https://inferencebench.io/2026-06-17daily1.0 https://inferencebench.io/bench/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/changelog/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-audit/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-bundle/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-cache/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-ci/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-compare/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-cost/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-diff/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-doctor/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-export/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-fetch/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-history/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-leaderboard/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-list/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-matrix/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-plugin/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-profile/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-publish/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-replay/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-run/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-schema/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-summary/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-verify/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/bench-watch/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/cli/overview/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/community/code-of-conduct/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/community/contributing/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/community/discussions/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/community/security/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/concepts/envelope/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/concepts/fingerprinting/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/concepts/methodology/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/concepts/pareto/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/concepts/reproducibility/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/concepts/vendor-neutrality/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/faq/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/install/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/integrations/github-actions/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/integrations/huggingface-hub/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/plugins/llm-inference/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/plugins/overview/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/quickstart/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/recipes/audit/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/recipes/ci-integration/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/recipes/concurrency-sweep/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/recipes/cross-model/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/recipes/docker/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/recipes/multi-vendor-marathon/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/recipes/multi-vendor-matrix/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/recipes/regression-check/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/recipes/reproducibility/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/recipes/sigstore-verification/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/recipes/voice-asr/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/reference/cli-reference/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/reference/envelope-schema/2026-06-17weekly0.5 https://inferencebench.io/bench/docs/tour/2026-06-17weekly0.5 https://inferencebench.io/bench/leaderboard/2026-06-17weekly0.5 https://inferencebench.io/blog/2026-06-17weekly0.8 https://inferencebench.io/blog/benchmarking-nvidia-alpamayo-1-5-10b-h100/2026-04-09monthly0.7 https://inferencebench.io/blog/flux2-klein-4b-image-generation-benchmark/2026-04-12monthly0.7 https://inferencebench.io/blog/gemma-4-31b-h100-complete-inference-benchmark/2026-04-09monthly0.7 https://inferencebench.io/blog/gemma-4-vs-moe-dense-model-wins/2026-04-12monthly0.7 https://inferencebench.io/blog/gpu-memory-wall-forecasting-ai-demand-2028/2026-04-12monthly0.7 https://inferencebench.io/blog/minimax-m25-229b-moe-honest-benchmark/2026-04-12monthly0.7 https://inferencebench.io/blog/minimax-m25-vs-m27-doubling-moe-params/2026-04-12monthly0.7 https://inferencebench.io/blog/minimax-m27-456b-bigger-moe-paradox/2026-04-12monthly0.7 https://inferencebench.io/blog/nemotron-super-120b-vs-ultra-253b-nvidia-showdown/2026-04-14monthly0.7 https://inferencebench.io/blog/nvidia-rubin-vera-next-gpu-revolution/2026-04-12monthly0.7 https://inferencebench.io/blog/qwen3-coder-the-model-that-does-everything-right/2026-04-14monthly0.7 https://inferencebench.io/blog/whisper-large-v3-turbo-597x-realtime-asr-benchmark/2026-04-13monthly0.7 https://inferencebench.io/calculator/2026-06-17weekly0.9 https://inferencebench.io/calculator/training/2026-06-17weekly0.5 https://inferencebench.io/community/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-34b-vs-01-ai--yi-1.5-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-34b-vs-01-ai--yi-coder-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-34b-vs-01-ai--yi-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-34b-vs-01-ai--yi-lightning/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-34b-vs-ai21--jamba-1.5-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-34b-vs-ai21--jamba-1.5-mini/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-34b-vs-alibaba--gte-qwen2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-34b-vs-alibaba--marco-o1/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-34b-vs-alibaba--qwen-1.5-moe-a2.7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-34b-vs-alibaba--qwen-2-audio-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-34b-vs-alibaba--qwen-2.5-14b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-34b-vs-alibaba--qwen-2.5-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-34b-vs-alibaba--qwen-2.5-3b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-34b-vs-alibaba--qwen-2.5-coder-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-34b-vs-allenai--molmo-72b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-34b-vs-allenai--olmo-2-13b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-34b-vs-allenai--olmo-2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-34b-vs-amazon--nova-lite/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-34b-vs-amazon--nova-pro/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-9b-vs-01-ai--yi-1.5-34b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-9b-vs-01-ai--yi-coder-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-9b-vs-01-ai--yi-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-9b-vs-01-ai--yi-lightning/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-9b-vs-ai21--jamba-1.5-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-9b-vs-ai21--jamba-1.5-mini/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-9b-vs-alibaba--gte-qwen2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-9b-vs-alibaba--marco-o1/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-9b-vs-alibaba--qwen-1.5-moe-a2.7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-9b-vs-alibaba--qwen-2-audio-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-9b-vs-alibaba--qwen-2.5-14b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-9b-vs-alibaba--qwen-2.5-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-9b-vs-alibaba--qwen-2.5-3b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-9b-vs-alibaba--qwen-2.5-coder-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-9b-vs-allenai--molmo-72b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-9b-vs-allenai--olmo-2-13b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-9b-vs-allenai--olmo-2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-9b-vs-amazon--nova-lite/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-1.5-9b-vs-amazon--nova-pro/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-coder-9b-vs-01-ai--yi-1.5-34b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-coder-9b-vs-01-ai--yi-1.5-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-coder-9b-vs-01-ai--yi-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-coder-9b-vs-01-ai--yi-lightning/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-coder-9b-vs-ai21--jamba-1.5-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-coder-9b-vs-ai21--jamba-1.5-mini/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-coder-9b-vs-alibaba--gte-qwen2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-coder-9b-vs-alibaba--marco-o1/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-coder-9b-vs-alibaba--qwen-1.5-moe-a2.7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-coder-9b-vs-alibaba--qwen-2-audio-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-coder-9b-vs-alibaba--qwen-2.5-14b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-coder-9b-vs-alibaba--qwen-2.5-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-coder-9b-vs-alibaba--qwen-2.5-3b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-coder-9b-vs-alibaba--qwen-2.5-coder-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-coder-9b-vs-allenai--molmo-72b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-coder-9b-vs-allenai--olmo-2-13b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-coder-9b-vs-allenai--olmo-2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-coder-9b-vs-amazon--nova-lite/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-coder-9b-vs-amazon--nova-pro/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-large-vs-01-ai--yi-1.5-34b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-large-vs-01-ai--yi-1.5-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-large-vs-01-ai--yi-coder-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-large-vs-01-ai--yi-lightning/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-large-vs-ai21--jamba-1.5-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-large-vs-ai21--jamba-1.5-mini/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-large-vs-alibaba--gte-qwen2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-large-vs-alibaba--marco-o1/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-large-vs-alibaba--qwen-1.5-moe-a2.7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-large-vs-alibaba--qwen-2-audio-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-large-vs-alibaba--qwen-2.5-14b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-large-vs-alibaba--qwen-2.5-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-large-vs-alibaba--qwen-2.5-3b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-large-vs-alibaba--qwen-2.5-coder-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-large-vs-allenai--molmo-72b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-large-vs-allenai--olmo-2-13b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-large-vs-allenai--olmo-2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-large-vs-amazon--nova-lite/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-large-vs-amazon--nova-pro/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-lightning-vs-01-ai--yi-1.5-34b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-lightning-vs-01-ai--yi-1.5-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-lightning-vs-01-ai--yi-coder-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-lightning-vs-01-ai--yi-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-lightning-vs-ai21--jamba-1.5-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-lightning-vs-ai21--jamba-1.5-mini/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-lightning-vs-alibaba--gte-qwen2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-lightning-vs-alibaba--marco-o1/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-lightning-vs-alibaba--qwen-1.5-moe-a2.7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-lightning-vs-alibaba--qwen-2-audio-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-lightning-vs-alibaba--qwen-2.5-14b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-lightning-vs-alibaba--qwen-2.5-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-lightning-vs-alibaba--qwen-2.5-3b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-lightning-vs-alibaba--qwen-2.5-coder-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-lightning-vs-allenai--molmo-72b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-lightning-vs-allenai--olmo-2-13b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-lightning-vs-allenai--olmo-2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-lightning-vs-amazon--nova-lite/2026-06-17weekly0.5 https://inferencebench.io/compare-models/01-ai--yi-lightning-vs-amazon--nova-pro/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-large-vs-01-ai--yi-1.5-34b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-large-vs-01-ai--yi-1.5-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-large-vs-01-ai--yi-coder-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-large-vs-01-ai--yi-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-large-vs-01-ai--yi-lightning/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-large-vs-ai21--jamba-1.5-mini/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-large-vs-alibaba--gte-qwen2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-large-vs-alibaba--marco-o1/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-large-vs-alibaba--qwen-1.5-moe-a2.7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-large-vs-alibaba--qwen-2-audio-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-large-vs-alibaba--qwen-2.5-14b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-large-vs-alibaba--qwen-2.5-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-large-vs-alibaba--qwen-2.5-3b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-large-vs-alibaba--qwen-2.5-coder-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-large-vs-allenai--molmo-72b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-large-vs-allenai--olmo-2-13b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-large-vs-allenai--olmo-2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-large-vs-amazon--nova-lite/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-large-vs-amazon--nova-pro/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-mini-vs-01-ai--yi-1.5-34b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-mini-vs-01-ai--yi-1.5-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-mini-vs-01-ai--yi-coder-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-mini-vs-01-ai--yi-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-mini-vs-01-ai--yi-lightning/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-mini-vs-ai21--jamba-1.5-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-mini-vs-alibaba--gte-qwen2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-mini-vs-alibaba--marco-o1/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-mini-vs-alibaba--qwen-1.5-moe-a2.7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-mini-vs-alibaba--qwen-2-audio-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-mini-vs-alibaba--qwen-2.5-14b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-mini-vs-alibaba--qwen-2.5-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-mini-vs-alibaba--qwen-2.5-3b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-mini-vs-alibaba--qwen-2.5-coder-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-mini-vs-allenai--molmo-72b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-mini-vs-allenai--olmo-2-13b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-mini-vs-allenai--olmo-2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-mini-vs-amazon--nova-lite/2026-06-17weekly0.5 https://inferencebench.io/compare-models/ai21--jamba-1.5-mini-vs-amazon--nova-pro/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--gte-qwen2-7b-vs-01-ai--yi-1.5-34b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--gte-qwen2-7b-vs-01-ai--yi-1.5-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--gte-qwen2-7b-vs-01-ai--yi-coder-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--gte-qwen2-7b-vs-01-ai--yi-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--gte-qwen2-7b-vs-01-ai--yi-lightning/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--gte-qwen2-7b-vs-ai21--jamba-1.5-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--gte-qwen2-7b-vs-ai21--jamba-1.5-mini/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--gte-qwen2-7b-vs-alibaba--marco-o1/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--gte-qwen2-7b-vs-alibaba--qwen-1.5-moe-a2.7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--gte-qwen2-7b-vs-alibaba--qwen-2-audio-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--gte-qwen2-7b-vs-alibaba--qwen-2.5-14b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--gte-qwen2-7b-vs-alibaba--qwen-2.5-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--gte-qwen2-7b-vs-alibaba--qwen-2.5-3b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--gte-qwen2-7b-vs-alibaba--qwen-2.5-coder-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--gte-qwen2-7b-vs-allenai--molmo-72b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--gte-qwen2-7b-vs-allenai--olmo-2-13b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--gte-qwen2-7b-vs-allenai--olmo-2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--gte-qwen2-7b-vs-amazon--nova-lite/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--gte-qwen2-7b-vs-amazon--nova-pro/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--marco-o1-vs-01-ai--yi-1.5-34b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--marco-o1-vs-01-ai--yi-1.5-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--marco-o1-vs-01-ai--yi-coder-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--marco-o1-vs-01-ai--yi-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--marco-o1-vs-01-ai--yi-lightning/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--marco-o1-vs-ai21--jamba-1.5-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--marco-o1-vs-ai21--jamba-1.5-mini/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--marco-o1-vs-alibaba--gte-qwen2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--marco-o1-vs-alibaba--qwen-1.5-moe-a2.7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--marco-o1-vs-alibaba--qwen-2-audio-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--marco-o1-vs-alibaba--qwen-2.5-14b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--marco-o1-vs-alibaba--qwen-2.5-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--marco-o1-vs-alibaba--qwen-2.5-3b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--marco-o1-vs-alibaba--qwen-2.5-coder-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--marco-o1-vs-allenai--molmo-72b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--marco-o1-vs-allenai--olmo-2-13b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--marco-o1-vs-allenai--olmo-2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--marco-o1-vs-amazon--nova-lite/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--marco-o1-vs-amazon--nova-pro/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-1.5-moe-a2.7b-vs-01-ai--yi-1.5-34b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-1.5-moe-a2.7b-vs-01-ai--yi-1.5-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-1.5-moe-a2.7b-vs-01-ai--yi-coder-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-1.5-moe-a2.7b-vs-01-ai--yi-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-1.5-moe-a2.7b-vs-01-ai--yi-lightning/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-1.5-moe-a2.7b-vs-ai21--jamba-1.5-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-1.5-moe-a2.7b-vs-ai21--jamba-1.5-mini/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-1.5-moe-a2.7b-vs-alibaba--gte-qwen2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-1.5-moe-a2.7b-vs-alibaba--marco-o1/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-1.5-moe-a2.7b-vs-alibaba--qwen-2-audio-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-1.5-moe-a2.7b-vs-alibaba--qwen-2.5-14b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-1.5-moe-a2.7b-vs-alibaba--qwen-2.5-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-1.5-moe-a2.7b-vs-alibaba--qwen-2.5-3b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-1.5-moe-a2.7b-vs-alibaba--qwen-2.5-coder-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-1.5-moe-a2.7b-vs-allenai--molmo-72b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-1.5-moe-a2.7b-vs-allenai--olmo-2-13b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-1.5-moe-a2.7b-vs-allenai--olmo-2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-1.5-moe-a2.7b-vs-amazon--nova-lite/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-1.5-moe-a2.7b-vs-amazon--nova-pro/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2-audio-7b-vs-01-ai--yi-1.5-34b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2-audio-7b-vs-01-ai--yi-1.5-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2-audio-7b-vs-01-ai--yi-coder-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2-audio-7b-vs-01-ai--yi-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2-audio-7b-vs-01-ai--yi-lightning/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2-audio-7b-vs-ai21--jamba-1.5-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2-audio-7b-vs-ai21--jamba-1.5-mini/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2-audio-7b-vs-alibaba--gte-qwen2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2-audio-7b-vs-alibaba--marco-o1/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2-audio-7b-vs-alibaba--qwen-1.5-moe-a2.7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2-audio-7b-vs-alibaba--qwen-2.5-14b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2-audio-7b-vs-alibaba--qwen-2.5-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2-audio-7b-vs-alibaba--qwen-2.5-3b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2-audio-7b-vs-alibaba--qwen-2.5-coder-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2-audio-7b-vs-allenai--molmo-72b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2-audio-7b-vs-allenai--olmo-2-13b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2-audio-7b-vs-allenai--olmo-2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2-audio-7b-vs-amazon--nova-lite/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2-audio-7b-vs-amazon--nova-pro/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-14b-vs-01-ai--yi-1.5-34b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-14b-vs-01-ai--yi-1.5-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-14b-vs-01-ai--yi-coder-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-14b-vs-01-ai--yi-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-14b-vs-01-ai--yi-lightning/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-14b-vs-ai21--jamba-1.5-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-14b-vs-ai21--jamba-1.5-mini/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-14b-vs-alibaba--gte-qwen2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-14b-vs-alibaba--marco-o1/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-14b-vs-alibaba--qwen-1.5-moe-a2.7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-14b-vs-alibaba--qwen-2-audio-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-14b-vs-alibaba--qwen-2.5-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-14b-vs-alibaba--qwen-2.5-3b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-14b-vs-alibaba--qwen-2.5-coder-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-14b-vs-allenai--molmo-72b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-14b-vs-allenai--olmo-2-13b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-14b-vs-allenai--olmo-2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-14b-vs-amazon--nova-lite/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-14b-vs-amazon--nova-pro/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-32b-vs-01-ai--yi-1.5-34b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-32b-vs-01-ai--yi-1.5-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-32b-vs-01-ai--yi-coder-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-32b-vs-01-ai--yi-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-32b-vs-01-ai--yi-lightning/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-32b-vs-ai21--jamba-1.5-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-32b-vs-ai21--jamba-1.5-mini/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-32b-vs-alibaba--gte-qwen2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-32b-vs-alibaba--marco-o1/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-32b-vs-alibaba--qwen-1.5-moe-a2.7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-32b-vs-alibaba--qwen-2-audio-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-32b-vs-alibaba--qwen-2.5-14b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-32b-vs-alibaba--qwen-2.5-3b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-32b-vs-alibaba--qwen-2.5-coder-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-32b-vs-allenai--molmo-72b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-32b-vs-allenai--olmo-2-13b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-32b-vs-allenai--olmo-2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-32b-vs-amazon--nova-lite/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-32b-vs-amazon--nova-pro/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-3b-vs-01-ai--yi-1.5-34b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-3b-vs-01-ai--yi-1.5-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-3b-vs-01-ai--yi-coder-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-3b-vs-01-ai--yi-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-3b-vs-01-ai--yi-lightning/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-3b-vs-ai21--jamba-1.5-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-3b-vs-ai21--jamba-1.5-mini/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-3b-vs-alibaba--gte-qwen2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-3b-vs-alibaba--marco-o1/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-3b-vs-alibaba--qwen-1.5-moe-a2.7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-3b-vs-alibaba--qwen-2-audio-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-3b-vs-alibaba--qwen-2.5-14b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-3b-vs-alibaba--qwen-2.5-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-3b-vs-alibaba--qwen-2.5-coder-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-3b-vs-allenai--molmo-72b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-3b-vs-allenai--olmo-2-13b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-3b-vs-allenai--olmo-2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-3b-vs-amazon--nova-lite/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-3b-vs-amazon--nova-pro/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-coder-32b-vs-01-ai--yi-1.5-34b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-coder-32b-vs-01-ai--yi-1.5-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-coder-32b-vs-01-ai--yi-coder-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-coder-32b-vs-01-ai--yi-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-coder-32b-vs-01-ai--yi-lightning/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-coder-32b-vs-ai21--jamba-1.5-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-coder-32b-vs-ai21--jamba-1.5-mini/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-coder-32b-vs-alibaba--gte-qwen2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-coder-32b-vs-alibaba--marco-o1/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-coder-32b-vs-alibaba--qwen-1.5-moe-a2.7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-coder-32b-vs-alibaba--qwen-2-audio-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-coder-32b-vs-alibaba--qwen-2.5-14b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-coder-32b-vs-alibaba--qwen-2.5-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-coder-32b-vs-alibaba--qwen-2.5-3b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-coder-32b-vs-allenai--molmo-72b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-coder-32b-vs-allenai--olmo-2-13b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-coder-32b-vs-allenai--olmo-2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-coder-32b-vs-amazon--nova-lite/2026-06-17weekly0.5 https://inferencebench.io/compare-models/alibaba--qwen-2.5-coder-32b-vs-amazon--nova-pro/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--molmo-72b-vs-01-ai--yi-1.5-34b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--molmo-72b-vs-01-ai--yi-1.5-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--molmo-72b-vs-01-ai--yi-coder-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--molmo-72b-vs-01-ai--yi-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--molmo-72b-vs-01-ai--yi-lightning/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--molmo-72b-vs-ai21--jamba-1.5-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--molmo-72b-vs-ai21--jamba-1.5-mini/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--molmo-72b-vs-alibaba--gte-qwen2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--molmo-72b-vs-alibaba--marco-o1/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--molmo-72b-vs-alibaba--qwen-1.5-moe-a2.7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--molmo-72b-vs-alibaba--qwen-2-audio-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--molmo-72b-vs-alibaba--qwen-2.5-14b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--molmo-72b-vs-alibaba--qwen-2.5-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--molmo-72b-vs-alibaba--qwen-2.5-3b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--molmo-72b-vs-alibaba--qwen-2.5-coder-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--molmo-72b-vs-allenai--olmo-2-13b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--molmo-72b-vs-allenai--olmo-2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--molmo-72b-vs-amazon--nova-lite/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--molmo-72b-vs-amazon--nova-pro/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-13b-vs-01-ai--yi-1.5-34b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-13b-vs-01-ai--yi-1.5-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-13b-vs-01-ai--yi-coder-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-13b-vs-01-ai--yi-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-13b-vs-01-ai--yi-lightning/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-13b-vs-ai21--jamba-1.5-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-13b-vs-ai21--jamba-1.5-mini/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-13b-vs-alibaba--gte-qwen2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-13b-vs-alibaba--marco-o1/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-13b-vs-alibaba--qwen-1.5-moe-a2.7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-13b-vs-alibaba--qwen-2-audio-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-13b-vs-alibaba--qwen-2.5-14b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-13b-vs-alibaba--qwen-2.5-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-13b-vs-alibaba--qwen-2.5-3b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-13b-vs-alibaba--qwen-2.5-coder-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-13b-vs-allenai--molmo-72b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-13b-vs-allenai--olmo-2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-13b-vs-amazon--nova-lite/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-13b-vs-amazon--nova-pro/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-7b-vs-01-ai--yi-1.5-34b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-7b-vs-01-ai--yi-1.5-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-7b-vs-01-ai--yi-coder-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-7b-vs-01-ai--yi-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-7b-vs-01-ai--yi-lightning/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-7b-vs-ai21--jamba-1.5-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-7b-vs-ai21--jamba-1.5-mini/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-7b-vs-alibaba--gte-qwen2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-7b-vs-alibaba--marco-o1/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-7b-vs-alibaba--qwen-1.5-moe-a2.7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-7b-vs-alibaba--qwen-2-audio-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-7b-vs-alibaba--qwen-2.5-14b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-7b-vs-alibaba--qwen-2.5-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-7b-vs-alibaba--qwen-2.5-3b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-7b-vs-alibaba--qwen-2.5-coder-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-7b-vs-allenai--molmo-72b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-7b-vs-allenai--olmo-2-13b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-7b-vs-amazon--nova-lite/2026-06-17weekly0.5 https://inferencebench.io/compare-models/allenai--olmo-2-7b-vs-amazon--nova-pro/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-lite-vs-01-ai--yi-1.5-34b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-lite-vs-01-ai--yi-1.5-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-lite-vs-01-ai--yi-coder-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-lite-vs-01-ai--yi-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-lite-vs-01-ai--yi-lightning/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-lite-vs-ai21--jamba-1.5-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-lite-vs-ai21--jamba-1.5-mini/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-lite-vs-alibaba--gte-qwen2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-lite-vs-alibaba--marco-o1/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-lite-vs-alibaba--qwen-1.5-moe-a2.7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-lite-vs-alibaba--qwen-2-audio-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-lite-vs-alibaba--qwen-2.5-14b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-lite-vs-alibaba--qwen-2.5-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-lite-vs-alibaba--qwen-2.5-3b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-lite-vs-alibaba--qwen-2.5-coder-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-lite-vs-allenai--molmo-72b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-lite-vs-allenai--olmo-2-13b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-lite-vs-allenai--olmo-2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-lite-vs-amazon--nova-pro/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-pro-vs-01-ai--yi-1.5-34b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-pro-vs-01-ai--yi-1.5-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-pro-vs-01-ai--yi-coder-9b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-pro-vs-01-ai--yi-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-pro-vs-01-ai--yi-lightning/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-pro-vs-ai21--jamba-1.5-large/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-pro-vs-ai21--jamba-1.5-mini/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-pro-vs-alibaba--gte-qwen2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-pro-vs-alibaba--marco-o1/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-pro-vs-alibaba--qwen-1.5-moe-a2.7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-pro-vs-alibaba--qwen-2-audio-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-pro-vs-alibaba--qwen-2.5-14b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-pro-vs-alibaba--qwen-2.5-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-pro-vs-alibaba--qwen-2.5-3b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-pro-vs-alibaba--qwen-2.5-coder-32b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-pro-vs-allenai--molmo-72b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-pro-vs-allenai--olmo-2-13b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-pro-vs-allenai--olmo-2-7b/2026-06-17weekly0.5 https://inferencebench.io/compare-models/amazon--nova-pro-vs-amazon--nova-lite/2026-06-17weekly0.5 https://inferencebench.io/compare/2026-06-17weekly0.7 https://inferencebench.io/compare/providers/aws-vs-azure/2026-06-17weekly0.7 https://inferencebench.io/compare/providers/aws-vs-gcp/2026-06-17weekly0.7 https://inferencebench.io/compare/providers/aws-vs-runpod/2026-06-17weekly0.7 https://inferencebench.io/compare/providers/deepinfra-vs-fireworks/2026-06-17weekly0.7 https://inferencebench.io/compare/providers/deepinfra-vs-together-ai/2026-06-17weekly0.7 https://inferencebench.io/compare/providers/gcp-vs-azure/2026-06-17weekly0.7 https://inferencebench.io/compare/providers/groq-vs-deepinfra/2026-06-17weekly0.7 https://inferencebench.io/compare/providers/groq-vs-fireworks/2026-06-17weekly0.7 https://inferencebench.io/compare/providers/groq-vs-together-ai/2026-06-17weekly0.7 https://inferencebench.io/compare/providers/lambda-vs-coreweave/2026-06-17weekly0.7 https://inferencebench.io/compare/providers/runpod-vs-coreweave/2026-06-17weekly0.7 https://inferencebench.io/compare/providers/runpod-vs-lambda/2026-06-17weekly0.7 https://inferencebench.io/compare/providers/runpod-vs-vast-ai/2026-06-17weekly0.7 https://inferencebench.io/compare/providers/together-ai-vs-fireworks/2026-06-17weekly0.7 https://inferencebench.io/compare/providers/together-ai-vs-replicate/2026-06-17weekly0.7 https://inferencebench.io/compliance/2026-06-17monthly0.3 https://inferencebench.io/cookies/2026-06-17monthly0.3 https://inferencebench.io/cost-to-run/01-ai/yi-1.5-34b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/01-ai/yi-1.5-9b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/01-ai/yi-coder-9b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/01-ai/yi-large/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/01-ai/yi-lightning/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/ai21/jamba-1.5-large/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/ai21/jamba-1.5-mini/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/alibaba/gte-qwen2-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/alibaba/marco-o1/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/alibaba/qwen-1.5-moe-a2.7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/alibaba/qwen-2-audio-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/alibaba/qwen-2.5-14b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/alibaba/qwen-2.5-32b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/alibaba/qwen-2.5-3b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/alibaba/qwen-2.5-coder-32b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/allenai/molmo-72b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/allenai/olmo-2-13b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/allenai/olmo-2-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/amazon/nova-lite/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/amazon/nova-pro/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/apple/openelm-3b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/arabic/jais-30b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/baai/bge-base-en-v1.5/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/baai/bge-large-en-v1.5/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/baai/bge-m3/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/baai/bge-small-en-v1.5/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/baichuan/baichuan2-13b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/baichuan/baichuan2-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/bigcode/octocoder-15b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/bigcode/santacoder-1.1b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/bigcode/starcoder2-15b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/bigcode/starcoder2-3b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/bigcode/starcoder2-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/black-forest-labs/flux-1-dev/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/black-forest-labs/flux-2/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/cerebras/btlm-3b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/cerebras/cerebras-gpt-13b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/codellama/codellama-70b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/cognitivecomputations/dolphin-2.9-72b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/cohere/aya-23-35b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/cohere/aya-23-8b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/cohere/command-r-08-2024/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/cohere/command-r-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/cohere/command-r-plus/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/cohere/command-r/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/cohere/embed-english-v3/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/databricks/dbrx-base/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/dbrx/dbrx-instruct/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/deepseek/deepseek-coder-33b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/deepseek/deepseek-coder-6.7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/deepseek/deepseek-coder-v2-236b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/deepseek/deepseek-llm-67b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/deepseek/deepseek-math-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/deepseek/deepseek-moe-16b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/deepseek/deepseek-r1-distill-1.5b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/deepseek/deepseek-r1-distill-14b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/deepseek/deepseek-r1-distill-32b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/deepseek/deepseek-r1-distill-70b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/deepseek/deepseek-r1-distill-8b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/deepseek/deepseek-r1/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/deepseek/deepseek-v2-lite/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/deepseek/deepseek-v2.5/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/deepseek/deepseek-v3-0324/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/deepseek/deepseek-v3/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/deepseek/janus-pro-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/falcon/falcon-180b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/falcon/falcon-40b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/falcon/falcon-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/finance/fingpt-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/google/codegemma-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/google/gemini-3/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/google/gemma-1.1-2b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/google/gemma-2-27b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/google/gemma-2-2b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/google/gemma-2-9b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/google/gemma-3-12b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/google/gemma-3-1b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/google/gemma-3-27b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/google/gemma-3-2b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/google/gemma-3-4b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/google/gemma-4-31b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/google/paligemma-3b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/google/recurrentgemma-2b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/gradient/llama-3-70b-1m/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/h2o/h2o-danube3-500m/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/huggingface/kokoro-82m/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/huggingface/smollm-135m/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/huggingface/smollm-360m/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/huggingface/smollm2-1.7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/huggingface/zephyr-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/internlm/internlm2.5-20b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/internlm/internlm2.5-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/internlm/internlm3-8b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/internlm/internvl2-26b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/intfloat/e5-mistral-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/intfloat/multilingual-e5-large/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/japanese/elyza-13b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/japanese/japanese-stablelm-70b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/jina/jina-embeddings-v3/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/kaist/prometheus-2-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/korean/kullm-12.8b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/legal/saullm-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/lmsys/vicuna-13b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/lmsys/vicuna-33b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/lmsys/vicuna-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/medical/biomistral-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/medical/meditron-70b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/codellama-13b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/codellama-34b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/codellama-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/llama-2-13b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/llama-2-70b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/llama-2-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/llama-3-70b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/llama-3-8b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/llama-3.1-405b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/llama-3.1-70b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/llama-3.1-8b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/llama-3.2-11b-vision/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/llama-3.2-1b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/llama-3.2-3b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/llama-3.2-90b-vision-instruct/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/llama-3.2-90b-vision/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/llama-3.3-70b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/llama-3.3-8b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/llama-4-maverick-400b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/llama-4-scout-17b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/llama-guard-3-1b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta-llama/llama-guard-3-8b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/meta/seamless-m4t-v2-large/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/microsoft/florence-2-large/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/microsoft/orca-2-13b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/microsoft/phi-1.5/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/microsoft/phi-1/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/microsoft/phi-2/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/microsoft/phi-3-medium-14b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/microsoft/phi-3-mini-3.8b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/microsoft/phi-3-small-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/microsoft/phi-3.5-moe/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/microsoft/phi-3.5-vision/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/microsoft/phi-4-mini/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/microsoft/phi-4/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/microsoft/wizardmath-70b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/minimax/minimax-m2-7/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/minimax/minimax-text-01/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/mistral/codestral-22b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/mistral/codestral-mamba-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/mistral/ministral-8b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/mistral/mistral-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/mistral/mistral-large-2411/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/mistral/mistral-large/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/mistral/mistral-medium-3/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/mistral/mistral-nemo-12b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/mistral/mistral-small-24b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/mistral/mistral-small-3.1-24b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/mistral/mixtral-8x22b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/mistral/mixtral-8x7b-instruct/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/mistral/mixtral-8x7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/mistral/pixtral-12b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/moonshot/kimi-k2.5/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/mosaicml/mpt-30b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/mosaicml/mpt-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nomic/nomic-embed-text-v1.5/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nousresearch/hermes-3-70b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nousresearch/hermes-3-8b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/alpamayo-10b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/canary-1b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/cosmos-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/eagle-2-1b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/eagle-2-9b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/eagle-2.5-8b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/helpsteer2-llama-3.1-70b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/llama-3.1-nemotron-51b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/llama-3.1-nemotron-70b-instruct/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/llama-3.1-nemotron-70b-reward/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/megatron-turing-530b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/minitron-4b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/minitron-8b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/nemotron-15b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/nemotron-340b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/nemotron-70b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/nemotron-mini-4b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/nemotron-super-120b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/nemotron-ultra-253b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/nv-embed-v2/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/nv-embedqa-e5-v5/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/nv-embedqa-mistral-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/nv-retriever-v1/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/nvlm-d-72b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/parakeet-ctc-0.6b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/parakeet-tdt-1.1b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/vila-1.5-13b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/vila-1.5-3b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/nvidia/vila-1.5-40b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/openai/dall-e-3/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/openai/whisper-base/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/openai/whisper-large-v3/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/openai/whisper-medium/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/openai/whisper-small/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/claude-3-opus/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/claude-3-sonnet/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/claude-haiku-3.5/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/claude-haiku-4-5/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/claude-opus-4-1/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/claude-opus-4-5/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/claude-opus-4-6/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/claude-opus-4-7/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/claude-opus-4/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/claude-sonnet-3-5/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/claude-sonnet-4-5/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/claude-sonnet-4-6/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/claude-sonnet-4/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/command-a/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/gemini-1.5-flash/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/gemini-1.5-pro/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/gemini-2.0-flash/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/gemini-2.0-pro/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/gpt-3.5-turbo/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/gpt-4-turbo/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/gpt-4.5-preview/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/gpt-4o-mini/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/gpt-4o/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/gpt-5-5/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/gpt-5-mini/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/gpt-5-nano/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/gpt-5/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/grok-3/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/inflection-3/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/jamba-instruct/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/llama-4-behemoth/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/o1-mini/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/o1/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/o3-mini/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/proprietary/reka-core/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-2-vl-2b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-2.5-0.5b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-2.5-1.5b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-2.5-72b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-2.5-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-2.5-coder-1.5b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-2.5-coder-14b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-2.5-coder-32b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-2.5-coder-3b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-2.5-coder-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-2.5-math-72b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-2.5-math-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-2.5-vl-72b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-2.5-vl-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-3-0.6b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-3-1.7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-3-235b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-3-30b-a3b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-3-32b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-3-4b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-3-8b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/qwen/qwen-3-coder-8b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/replit/replit-code-v1.5-3b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/rinna/nekomata-14b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/rwkv/rwkv-6-14b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/sail/infoxlm-large/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/salesforce/codegen2-16b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/sberbank/gigachat-20b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/scientific/sciglm-6b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/sensetime/internlm-20b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/sentence-transformers/all-minilm-l6-v2/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/sesame/csm-1b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/snowflake/arctic-128x3b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/snowflake/arctic-480b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/stabilityai/sdxl-1.0/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/stabilityai/stablelm-2-12b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/stabilityai/stablelm-zephyr-3b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/teknium/openhermes-2.5-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/thudm/chatglm3-6b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/thudm/cogvlm2-19b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/tiiuae/falcon-11b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/tiiuae/falcon-3-10b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/tiiuae/falcon-3-1b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/tiiuae/falcon-3-3b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/tiiuae/falcon-3-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/tiiuae/falcon-mamba-7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/tinyllama/tinyllama-1.1b-chat/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/tinyllama/tinyllama-1.1b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/together/llama-3.1-70b-turbo/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/upstage/solar-10.7b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/upstage/solar-pro-22b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/vikhyat/moondream-2b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/wizardlm/wizardcoder-33b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/xai/grok-2/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/xai/grok-3-mini/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/xai/grok-3/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/xai/grok-4-3/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/xai/grok-4/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/yandex/yalm-100b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/yilai/yi-6b-200k/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/zhipu/chatglm4-9b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/zhipu/glm-4-9b/2026-06-17weekly0.6 https://inferencebench.io/cost-to-run/zhipu/glm-5/2026-06-17weekly0.6 https://inferencebench.io/data-license/2026-06-17monthly0.3 https://inferencebench.io/developers/2026-06-17weekly0.5 https://inferencebench.io/glossary/2026-06-17weekly0.5 https://inferencebench.io/gpus/2026-06-17weekly0.8 https://inferencebench.io/gpus/amd-mi100/2026-06-17weekly0.6 https://inferencebench.io/gpus/amd-mi210/2026-06-17weekly0.6 https://inferencebench.io/gpus/amd-mi250x/2026-06-17weekly0.6 https://inferencebench.io/gpus/amd-mi300x/2026-06-17weekly0.6 https://inferencebench.io/gpus/amd-mi325x/2026-06-17weekly0.6 https://inferencebench.io/gpus/amd-rx-7900-xtx/2026-06-17weekly0.6 https://inferencebench.io/gpus/amd-w7900/2026-06-17weekly0.6 https://inferencebench.io/gpus/aws-trainium2/2026-06-17weekly0.6 https://inferencebench.io/gpus/compare/nvidia-a100-80gb-sxm-vs-amd-mi300x/2026-06-17weekly0.5 https://inferencebench.io/gpus/compare/nvidia-a100-80gb-sxm-vs-nvidia-a100-40gb-sxm/2026-06-17weekly0.5 https://inferencebench.io/gpus/compare/nvidia-a100-80gb-sxm-vs-nvidia-a100-80gb-pcie/2026-06-17weekly0.5 https://inferencebench.io/gpus/compare/nvidia-a100-80gb-sxm-vs-nvidia-l40s/2026-06-17weekly0.5 https://inferencebench.io/gpus/compare/nvidia-a6000-vs-nvidia-l40s/2026-06-17weekly0.5 https://inferencebench.io/gpus/compare/nvidia-b200-sxm-vs-nvidia-b100-sxm/2026-06-17weekly0.5 https://inferencebench.io/gpus/compare/nvidia-b200-sxm-vs-nvidia-h200-sxm/2026-06-17weekly0.5 https://inferencebench.io/gpus/compare/nvidia-h100-nvl-vs-nvidia-h100-sxm/2026-06-17weekly0.5 https://inferencebench.io/gpus/compare/nvidia-h100-sxm-vs-amd-mi300x/2026-06-17weekly0.5 https://inferencebench.io/gpus/compare/nvidia-h100-sxm-vs-nvidia-a100-80gb-sxm/2026-06-17weekly0.5 https://inferencebench.io/gpus/compare/nvidia-h100-sxm-vs-nvidia-b200-sxm/2026-06-17weekly0.5 https://inferencebench.io/gpus/compare/nvidia-h100-sxm-vs-nvidia-h100-pcie/2026-06-17weekly0.5 https://inferencebench.io/gpus/compare/nvidia-h100-sxm-vs-nvidia-l40s/2026-06-17weekly0.5 https://inferencebench.io/gpus/compare/nvidia-h200-sxm-vs-nvidia-a100-80gb-sxm/2026-06-17weekly0.5 https://inferencebench.io/gpus/compare/nvidia-h200-sxm-vs-nvidia-h100-sxm/2026-06-17weekly0.5 https://inferencebench.io/gpus/compare/nvidia-l4-vs-nvidia-t4/2026-06-17weekly0.5 https://inferencebench.io/gpus/compare/nvidia-l40s-vs-nvidia-l40/2026-06-17weekly0.5 https://inferencebench.io/gpus/compare/nvidia-rtx-3090-vs-nvidia-rtx-4090/2026-06-17weekly0.5 https://inferencebench.io/gpus/compare/nvidia-rtx-4090-vs-nvidia-l40s/2026-06-17weekly0.5 https://inferencebench.io/gpus/compare/nvidia-rtx-4090-vs-nvidia-rtx-5090/2026-06-17weekly0.5 https://inferencebench.io/gpus/google-tpu-v4/2026-06-17weekly0.6 https://inferencebench.io/gpus/google-tpu-v5e/2026-06-17weekly0.6 https://inferencebench.io/gpus/google-tpu-v6e/2026-06-17weekly0.6 https://inferencebench.io/gpus/groq-lpu/2026-06-17weekly0.6 https://inferencebench.io/gpus/intel-gaudi-2/2026-06-17weekly0.6 https://inferencebench.io/gpus/intel-gaudi-3-hl325l/2026-06-17weekly0.6 https://inferencebench.io/gpus/intel-gaudi-3/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-a100-40gb-pcie/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-a100-40gb-sxm/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-a100-80gb-pcie/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-a100-80gb-sxm/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-a10g/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-a16/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-a2/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-a30/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-a40/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-a4000/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-a6000/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-b100-sxm/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-b200-nvl/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-b200-sxm/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-b300/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-gb200-nvl72/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-gb300-nvl72/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-gh200/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-h100-nvl-94gb/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-h100-nvl/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-h100-pcie/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-h100-sxm/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-h20/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-h200-sxm/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-l20/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-l4/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-l40/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-l40s/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-rtx-3060/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-rtx-3070/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-rtx-3080/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-rtx-3090/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-rtx-4060-ti-16gb/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-rtx-4060/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-rtx-4070-super/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-rtx-4070-ti/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-rtx-4080/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-rtx-4090/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-rtx-5090/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-rtx-6000-ada/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-rtx-a5000/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-t4/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-v100-16gb/2026-06-17weekly0.6 https://inferencebench.io/gpus/nvidia-v100-32gb/2026-06-17weekly0.6 https://inferencebench.io/gpus/qualcomm-cloud-ai-100/2026-06-17weekly0.6 https://inferencebench.io/infrastructure/2026-06-17weekly0.9 https://inferencebench.io/infrastructure/data-centers/2026-06-17weekly0.6 https://inferencebench.io/infrastructure/ixps/2026-06-17weekly0.5 https://inferencebench.io/infrastructure/leaderboard/2026-06-17weekly0.7 https://inferencebench.io/infrastructure/sustainability/2026-06-17weekly0.7 https://inferencebench.io/leaderboard/2026-06-17daily1.0 https://inferencebench.io/leaderboard/training/2026-06-17weekly0.5 https://inferencebench.io/licenses/2026-06-17monthly0.3 https://inferencebench.io/methodology/2026-06-17weekly0.5 https://inferencebench.io/methodology/inference-score/2026-06-17weekly0.5 https://inferencebench.io/models/2026-06-17daily0.9 https://inferencebench.io/models/01-ai/yi-1.5-34b/2026-06-17weekly0.7 https://inferencebench.io/models/01-ai/yi-1.5-9b/2026-06-17weekly0.7 https://inferencebench.io/models/01-ai/yi-coder-9b/2026-06-17weekly0.7 https://inferencebench.io/models/01-ai/yi-large/2026-06-17weekly0.7 https://inferencebench.io/models/01-ai/yi-lightning/2026-06-17weekly0.7 https://inferencebench.io/models/ai21/jamba-1.5-large/2026-06-17weekly0.7 https://inferencebench.io/models/ai21/jamba-1.5-mini/2026-06-17weekly0.7 https://inferencebench.io/models/alibaba/gte-qwen2-7b/2026-06-17weekly0.7 https://inferencebench.io/models/alibaba/marco-o1/2026-06-17weekly0.7 https://inferencebench.io/models/alibaba/qwen-1.5-moe-a2.7b/2026-06-17weekly0.7 https://inferencebench.io/models/alibaba/qwen-2-audio-7b/2026-06-17weekly0.7 https://inferencebench.io/models/alibaba/qwen-2.5-14b/2026-06-17weekly0.7 https://inferencebench.io/models/alibaba/qwen-2.5-32b/2026-06-17weekly0.7 https://inferencebench.io/models/alibaba/qwen-2.5-3b/2026-06-17weekly0.7 https://inferencebench.io/models/alibaba/qwen-2.5-coder-32b/2026-06-17weekly0.7 https://inferencebench.io/models/allenai/molmo-72b/2026-06-17weekly0.7 https://inferencebench.io/models/allenai/olmo-2-13b/2026-06-17weekly0.7 https://inferencebench.io/models/allenai/olmo-2-7b/2026-06-17weekly0.7 https://inferencebench.io/models/amazon/nova-lite/2026-06-17weekly0.7 https://inferencebench.io/models/amazon/nova-pro/2026-06-17weekly0.7 https://inferencebench.io/models/apple/openelm-3b/2026-06-17weekly0.7 https://inferencebench.io/models/arabic/jais-30b/2026-06-17weekly0.7 https://inferencebench.io/models/baai/bge-base-en-v1.5/2026-06-17weekly0.7 https://inferencebench.io/models/baai/bge-large-en-v1.5/2026-06-17weekly0.7 https://inferencebench.io/models/baai/bge-m3/2026-06-17weekly0.7 https://inferencebench.io/models/baai/bge-small-en-v1.5/2026-06-17weekly0.7 https://inferencebench.io/models/baichuan/baichuan2-13b/2026-06-17weekly0.7 https://inferencebench.io/models/baichuan/baichuan2-7b/2026-06-17weekly0.7 https://inferencebench.io/models/bigcode/octocoder-15b/2026-06-17weekly0.7 https://inferencebench.io/models/bigcode/santacoder-1.1b/2026-06-17weekly0.7 https://inferencebench.io/models/bigcode/starcoder2-15b/2026-06-17weekly0.7 https://inferencebench.io/models/bigcode/starcoder2-3b/2026-06-17weekly0.7 https://inferencebench.io/models/bigcode/starcoder2-7b/2026-06-17weekly0.7 https://inferencebench.io/models/black-forest-labs/flux-1-dev/2026-06-17weekly0.7 https://inferencebench.io/models/black-forest-labs/flux-2/2026-06-17weekly0.7 https://inferencebench.io/models/cerebras/btlm-3b/2026-06-17weekly0.7 https://inferencebench.io/models/cerebras/cerebras-gpt-13b/2026-06-17weekly0.7 https://inferencebench.io/models/codellama/codellama-70b/2026-06-17weekly0.7 https://inferencebench.io/models/cognitivecomputations/dolphin-2.9-72b/2026-06-17weekly0.7 https://inferencebench.io/models/cohere/aya-23-35b/2026-06-17weekly0.7 https://inferencebench.io/models/cohere/aya-23-8b/2026-06-17weekly0.7 https://inferencebench.io/models/cohere/command-r-08-2024/2026-06-17weekly0.7 https://inferencebench.io/models/cohere/command-r-7b/2026-06-17weekly0.7 https://inferencebench.io/models/cohere/command-r-plus/2026-06-17weekly0.7 https://inferencebench.io/models/cohere/command-r/2026-06-17weekly0.7 https://inferencebench.io/models/cohere/embed-english-v3/2026-06-17weekly0.7 https://inferencebench.io/models/databricks/dbrx-base/2026-06-17weekly0.7 https://inferencebench.io/models/dbrx/dbrx-instruct/2026-06-17weekly0.7 https://inferencebench.io/models/deepseek/deepseek-coder-33b/2026-06-17weekly0.7 https://inferencebench.io/models/deepseek/deepseek-coder-6.7b/2026-06-17weekly0.7 https://inferencebench.io/models/deepseek/deepseek-coder-v2-236b/2026-06-17weekly0.7 https://inferencebench.io/models/deepseek/deepseek-llm-67b/2026-06-17weekly0.7 https://inferencebench.io/models/deepseek/deepseek-math-7b/2026-06-17weekly0.7 https://inferencebench.io/models/deepseek/deepseek-moe-16b/2026-06-17weekly0.7 https://inferencebench.io/models/deepseek/deepseek-r1-distill-1.5b/2026-06-17weekly0.7 https://inferencebench.io/models/deepseek/deepseek-r1-distill-14b/2026-06-17weekly0.7 https://inferencebench.io/models/deepseek/deepseek-r1-distill-32b/2026-06-17weekly0.7 https://inferencebench.io/models/deepseek/deepseek-r1-distill-70b/2026-06-17weekly0.7 https://inferencebench.io/models/deepseek/deepseek-r1-distill-8b/2026-06-17weekly0.7 https://inferencebench.io/models/deepseek/deepseek-r1/2026-06-17weekly0.7 https://inferencebench.io/models/deepseek/deepseek-v2-lite/2026-06-17weekly0.7 https://inferencebench.io/models/deepseek/deepseek-v2.5/2026-06-17weekly0.7 https://inferencebench.io/models/deepseek/deepseek-v3-0324/2026-06-17weekly0.7 https://inferencebench.io/models/deepseek/deepseek-v3/2026-06-17weekly0.7 https://inferencebench.io/models/deepseek/janus-pro-7b/2026-06-17weekly0.7 https://inferencebench.io/models/falcon/falcon-180b/2026-06-17weekly0.7 https://inferencebench.io/models/falcon/falcon-40b/2026-06-17weekly0.7 https://inferencebench.io/models/falcon/falcon-7b/2026-06-17weekly0.7 https://inferencebench.io/models/finance/fingpt-7b/2026-06-17weekly0.7 https://inferencebench.io/models/google/codegemma-7b/2026-06-17weekly0.7 https://inferencebench.io/models/google/gemini-3/2026-06-17weekly0.7 https://inferencebench.io/models/google/gemma-1.1-2b/2026-06-17weekly0.7 https://inferencebench.io/models/google/gemma-2-27b/2026-06-17weekly0.7 https://inferencebench.io/models/google/gemma-2-2b/2026-06-17weekly0.7 https://inferencebench.io/models/google/gemma-2-9b/2026-06-17weekly0.7 https://inferencebench.io/models/google/gemma-3-12b/2026-06-17weekly0.7 https://inferencebench.io/models/google/gemma-3-1b/2026-06-17weekly0.7 https://inferencebench.io/models/google/gemma-3-27b/2026-06-17weekly0.7 https://inferencebench.io/models/google/gemma-3-2b/2026-06-17weekly0.7 https://inferencebench.io/models/google/gemma-3-4b/2026-06-17weekly0.7 https://inferencebench.io/models/google/gemma-4-31b/2026-06-17weekly0.7 https://inferencebench.io/models/google/paligemma-3b/2026-06-17weekly0.7 https://inferencebench.io/models/google/recurrentgemma-2b/2026-06-17weekly0.7 https://inferencebench.io/models/gradient/llama-3-70b-1m/2026-06-17weekly0.7 https://inferencebench.io/models/h2o/h2o-danube3-500m/2026-06-17weekly0.7 https://inferencebench.io/models/huggingface/kokoro-82m/2026-06-17weekly0.7 https://inferencebench.io/models/huggingface/smollm-135m/2026-06-17weekly0.7 https://inferencebench.io/models/huggingface/smollm-360m/2026-06-17weekly0.7 https://inferencebench.io/models/huggingface/smollm2-1.7b/2026-06-17weekly0.7 https://inferencebench.io/models/huggingface/zephyr-7b/2026-06-17weekly0.7 https://inferencebench.io/models/internlm/internlm2.5-20b/2026-06-17weekly0.7 https://inferencebench.io/models/internlm/internlm2.5-7b/2026-06-17weekly0.7 https://inferencebench.io/models/internlm/internlm3-8b/2026-06-17weekly0.7 https://inferencebench.io/models/internlm/internvl2-26b/2026-06-17weekly0.7 https://inferencebench.io/models/intfloat/e5-mistral-7b/2026-06-17weekly0.7 https://inferencebench.io/models/intfloat/multilingual-e5-large/2026-06-17weekly0.7 https://inferencebench.io/models/japanese/elyza-13b/2026-06-17weekly0.7 https://inferencebench.io/models/japanese/japanese-stablelm-70b/2026-06-17weekly0.7 https://inferencebench.io/models/jina/jina-embeddings-v3/2026-06-17weekly0.7 https://inferencebench.io/models/kaist/prometheus-2-7b/2026-06-17weekly0.7 https://inferencebench.io/models/korean/kullm-12.8b/2026-06-17weekly0.7 https://inferencebench.io/models/legal/saullm-7b/2026-06-17weekly0.7 https://inferencebench.io/models/lmsys/vicuna-13b/2026-06-17weekly0.7 https://inferencebench.io/models/lmsys/vicuna-33b/2026-06-17weekly0.7 https://inferencebench.io/models/lmsys/vicuna-7b/2026-06-17weekly0.7 https://inferencebench.io/models/medical/biomistral-7b/2026-06-17weekly0.7 https://inferencebench.io/models/medical/meditron-70b/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/codellama-13b/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/codellama-34b/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/codellama-7b/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/llama-2-13b/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/llama-2-70b/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/llama-2-7b/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/llama-3-70b/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/llama-3-8b/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/llama-3.1-405b/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/llama-3.1-70b/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/llama-3.1-8b/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/llama-3.2-11b-vision/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/llama-3.2-1b/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/llama-3.2-3b/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/llama-3.2-90b-vision-instruct/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/llama-3.2-90b-vision/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/llama-3.3-70b/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/llama-3.3-8b/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/llama-4-maverick-400b/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/llama-4-scout-17b/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/llama-guard-3-1b/2026-06-17weekly0.7 https://inferencebench.io/models/meta-llama/llama-guard-3-8b/2026-06-17weekly0.7 https://inferencebench.io/models/meta/seamless-m4t-v2-large/2026-06-17weekly0.7 https://inferencebench.io/models/microsoft/florence-2-large/2026-06-17weekly0.7 https://inferencebench.io/models/microsoft/orca-2-13b/2026-06-17weekly0.7 https://inferencebench.io/models/microsoft/phi-1.5/2026-06-17weekly0.7 https://inferencebench.io/models/microsoft/phi-1/2026-06-17weekly0.7 https://inferencebench.io/models/microsoft/phi-2/2026-06-17weekly0.7 https://inferencebench.io/models/microsoft/phi-3-medium-14b/2026-06-17weekly0.7 https://inferencebench.io/models/microsoft/phi-3-mini-3.8b/2026-06-17weekly0.7 https://inferencebench.io/models/microsoft/phi-3-small-7b/2026-06-17weekly0.7 https://inferencebench.io/models/microsoft/phi-3.5-moe/2026-06-17weekly0.7 https://inferencebench.io/models/microsoft/phi-3.5-vision/2026-06-17weekly0.7 https://inferencebench.io/models/microsoft/phi-4-mini/2026-06-17weekly0.7 https://inferencebench.io/models/microsoft/phi-4/2026-06-17weekly0.7 https://inferencebench.io/models/microsoft/wizardmath-70b/2026-06-17weekly0.7 https://inferencebench.io/models/minimax/minimax-m2-7/2026-06-17weekly0.7 https://inferencebench.io/models/minimax/minimax-text-01/2026-06-17weekly0.7 https://inferencebench.io/models/mistral/codestral-22b/2026-06-17weekly0.7 https://inferencebench.io/models/mistral/codestral-mamba-7b/2026-06-17weekly0.7 https://inferencebench.io/models/mistral/ministral-8b/2026-06-17weekly0.7 https://inferencebench.io/models/mistral/mistral-7b/2026-06-17weekly0.7 https://inferencebench.io/models/mistral/mistral-large-2411/2026-06-17weekly0.7 https://inferencebench.io/models/mistral/mistral-large/2026-06-17weekly0.7 https://inferencebench.io/models/mistral/mistral-medium-3/2026-06-17weekly0.7 https://inferencebench.io/models/mistral/mistral-nemo-12b/2026-06-17weekly0.7 https://inferencebench.io/models/mistral/mistral-small-24b/2026-06-17weekly0.7 https://inferencebench.io/models/mistral/mistral-small-3.1-24b/2026-06-17weekly0.7 https://inferencebench.io/models/mistral/mixtral-8x22b/2026-06-17weekly0.7 https://inferencebench.io/models/mistral/mixtral-8x7b-instruct/2026-06-17weekly0.7 https://inferencebench.io/models/mistral/mixtral-8x7b/2026-06-17weekly0.7 https://inferencebench.io/models/mistral/pixtral-12b/2026-06-17weekly0.7 https://inferencebench.io/models/moonshot/kimi-k2.5/2026-06-17weekly0.7 https://inferencebench.io/models/mosaicml/mpt-30b/2026-06-17weekly0.7 https://inferencebench.io/models/mosaicml/mpt-7b/2026-06-17weekly0.7 https://inferencebench.io/models/nomic/nomic-embed-text-v1.5/2026-06-17weekly0.7 https://inferencebench.io/models/nousresearch/hermes-3-70b/2026-06-17weekly0.7 https://inferencebench.io/models/nousresearch/hermes-3-8b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/alpamayo-10b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/canary-1b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/cosmos-7b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/eagle-2-1b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/eagle-2-9b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/eagle-2.5-8b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/helpsteer2-llama-3.1-70b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/llama-3.1-nemotron-51b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/llama-3.1-nemotron-70b-instruct/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/llama-3.1-nemotron-70b-reward/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/megatron-turing-530b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/minitron-4b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/minitron-8b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/nemotron-15b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/nemotron-340b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/nemotron-70b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/nemotron-mini-4b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/nemotron-super-120b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/nemotron-ultra-253b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/nv-embed-v2/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/nv-embedqa-e5-v5/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/nv-embedqa-mistral-7b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/nv-retriever-v1/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/nvlm-d-72b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/parakeet-ctc-0.6b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/parakeet-tdt-1.1b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/vila-1.5-13b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/vila-1.5-3b/2026-06-17weekly0.7 https://inferencebench.io/models/nvidia/vila-1.5-40b/2026-06-17weekly0.7 https://inferencebench.io/models/openai/dall-e-3/2026-06-17weekly0.7 https://inferencebench.io/models/openai/gpt-5-5-instant/2026-06-17weekly0.7 https://inferencebench.io/models/openai/gpt-5-5-with-trusted-access-for-cyber/2026-06-17weekly0.7 https://inferencebench.io/models/openai/whisper-base/2026-06-17weekly0.7 https://inferencebench.io/models/openai/whisper-large-v3/2026-06-17weekly0.7 https://inferencebench.io/models/openai/whisper-medium/2026-06-17weekly0.7 https://inferencebench.io/models/openai/whisper-small/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/claude-3-opus/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/claude-3-sonnet/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/claude-haiku-3.5/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/claude-haiku-4-5/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/claude-opus-4-1/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/claude-opus-4-5/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/claude-opus-4-6/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/claude-opus-4-7/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/claude-opus-4/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/claude-sonnet-3-5/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/claude-sonnet-4-5/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/claude-sonnet-4-6/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/claude-sonnet-4/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/command-a/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/gemini-1.5-flash/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/gemini-1.5-pro/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/gemini-2.0-flash/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/gemini-2.0-pro/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/gpt-3.5-turbo/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/gpt-4-turbo/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/gpt-4.5-preview/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/gpt-4o-mini/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/gpt-4o/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/gpt-5-5/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/gpt-5-mini/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/gpt-5-nano/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/gpt-5/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/grok-3/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/inflection-3/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/jamba-instruct/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/llama-4-behemoth/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/o1-mini/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/o1/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/o3-mini/2026-06-17weekly0.7 https://inferencebench.io/models/proprietary/reka-core/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-2-vl-2b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-2.5-0.5b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-2.5-1.5b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-2.5-72b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-2.5-7b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-2.5-coder-1.5b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-2.5-coder-14b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-2.5-coder-32b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-2.5-coder-3b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-2.5-coder-7b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-2.5-math-72b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-2.5-math-7b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-2.5-vl-72b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-2.5-vl-7b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-3-0.6b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-3-1.7b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-3-235b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-3-30b-a3b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-3-32b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-3-4b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-3-8b/2026-06-17weekly0.7 https://inferencebench.io/models/qwen/qwen-3-coder-8b/2026-06-17weekly0.7 https://inferencebench.io/models/replit/replit-code-v1.5-3b/2026-06-17weekly0.7 https://inferencebench.io/models/rinna/nekomata-14b/2026-06-17weekly0.7 https://inferencebench.io/models/rwkv/rwkv-6-14b/2026-06-17weekly0.7 https://inferencebench.io/models/sail/infoxlm-large/2026-06-17weekly0.7 https://inferencebench.io/models/salesforce/codegen2-16b/2026-06-17weekly0.7 https://inferencebench.io/models/sberbank/gigachat-20b/2026-06-17weekly0.7 https://inferencebench.io/models/scientific/sciglm-6b/2026-06-17weekly0.7 https://inferencebench.io/models/sensetime/internlm-20b/2026-06-17weekly0.7 https://inferencebench.io/models/sentence-transformers/all-minilm-l6-v2/2026-06-17weekly0.7 https://inferencebench.io/models/sesame/csm-1b/2026-06-17weekly0.7 https://inferencebench.io/models/snowflake/arctic-128x3b/2026-06-17weekly0.7 https://inferencebench.io/models/snowflake/arctic-480b/2026-06-17weekly0.7 https://inferencebench.io/models/stabilityai/sdxl-1.0/2026-06-17weekly0.7 https://inferencebench.io/models/stabilityai/stablelm-2-12b/2026-06-17weekly0.7 https://inferencebench.io/models/stabilityai/stablelm-zephyr-3b/2026-06-17weekly0.7 https://inferencebench.io/models/teknium/openhermes-2.5-7b/2026-06-17weekly0.7 https://inferencebench.io/models/thudm/chatglm3-6b/2026-06-17weekly0.7 https://inferencebench.io/models/thudm/cogvlm2-19b/2026-06-17weekly0.7 https://inferencebench.io/models/tiiuae/falcon-11b/2026-06-17weekly0.7 https://inferencebench.io/models/tiiuae/falcon-3-10b/2026-06-17weekly0.7 https://inferencebench.io/models/tiiuae/falcon-3-1b/2026-06-17weekly0.7 https://inferencebench.io/models/tiiuae/falcon-3-3b/2026-06-17weekly0.7 https://inferencebench.io/models/tiiuae/falcon-3-7b/2026-06-17weekly0.7 https://inferencebench.io/models/tiiuae/falcon-mamba-7b/2026-06-17weekly0.7 https://inferencebench.io/models/tinyllama/tinyllama-1.1b-chat/2026-06-17weekly0.7 https://inferencebench.io/models/tinyllama/tinyllama-1.1b/2026-06-17weekly0.7 https://inferencebench.io/models/together/llama-3.1-70b-turbo/2026-06-17weekly0.7 https://inferencebench.io/models/upstage/solar-10.7b/2026-06-17weekly0.7 https://inferencebench.io/models/upstage/solar-pro-22b/2026-06-17weekly0.7 https://inferencebench.io/models/vikhyat/moondream-2b/2026-06-17weekly0.7 https://inferencebench.io/models/wizardlm/wizardcoder-33b/2026-06-17weekly0.7 https://inferencebench.io/models/xai/grok-2/2026-06-17weekly0.7 https://inferencebench.io/models/xai/grok-3-mini/2026-06-17weekly0.7 https://inferencebench.io/models/xai/grok-3/2026-06-17weekly0.7 https://inferencebench.io/models/xai/grok-4-3/2026-06-17weekly0.7 https://inferencebench.io/models/xai/grok-4/2026-06-17weekly0.7 https://inferencebench.io/models/yandex/yalm-100b/2026-06-17weekly0.7 https://inferencebench.io/models/yilai/yi-6b-200k/2026-06-17weekly0.7 https://inferencebench.io/models/zhipu/chatglm4-9b/2026-06-17weekly0.7 https://inferencebench.io/models/zhipu/glm-4-9b/2026-06-17weekly0.7 https://inferencebench.io/models/zhipu/glm-5/2026-06-17weekly0.7 https://inferencebench.io/pricing/2026-06-17weekly0.5 https://inferencebench.io/privacy/2026-06-17monthly0.3 https://inferencebench.io/providers/2026-06-17weekly0.8 https://inferencebench.io/providers/aws/2026-06-17weekly0.7 https://inferencebench.io/providers/aws/reviews/2026-06-17weekly0.7 https://inferencebench.io/providers/azure/2026-06-17weekly0.7 https://inferencebench.io/providers/azure/reviews/2026-06-17weekly0.7 https://inferencebench.io/providers/coreweave/2026-06-17weekly0.7 https://inferencebench.io/providers/coreweave/reviews/2026-06-17weekly0.7 https://inferencebench.io/providers/deepinfra/2026-06-17weekly0.7 https://inferencebench.io/providers/deepinfra/reviews/2026-06-17weekly0.7 https://inferencebench.io/providers/deepseek/2026-06-17weekly0.7 https://inferencebench.io/providers/deepseek/reviews/2026-06-17weekly0.7 https://inferencebench.io/providers/fireworks/2026-06-17weekly0.7 https://inferencebench.io/providers/fireworks/reviews/2026-06-17weekly0.7 https://inferencebench.io/providers/fluidstack/2026-06-17weekly0.7 https://inferencebench.io/providers/fluidstack/reviews/2026-06-17weekly0.7 https://inferencebench.io/providers/gcp/2026-06-17weekly0.7 https://inferencebench.io/providers/gcp/reviews/2026-06-17weekly0.7 https://inferencebench.io/providers/gpu-finder/2026-06-17weekly0.7 https://inferencebench.io/providers/groq/2026-06-17weekly0.7 https://inferencebench.io/providers/groq/reviews/2026-06-17weekly0.7 https://inferencebench.io/providers/huggingface/2026-06-17weekly0.7 https://inferencebench.io/providers/huggingface/reviews/2026-06-17weekly0.7 https://inferencebench.io/providers/hyperbolic/2026-06-17weekly0.7 https://inferencebench.io/providers/hyperbolic/reviews/2026-06-17weekly0.7 https://inferencebench.io/providers/lambda/2026-06-17weekly0.7 https://inferencebench.io/providers/lambda/reviews/2026-06-17weekly0.7 https://inferencebench.io/providers/novita/2026-06-17weekly0.7 https://inferencebench.io/providers/novita/reviews/2026-06-17weekly0.7 https://inferencebench.io/providers/replicate/2026-06-17weekly0.7 https://inferencebench.io/providers/replicate/reviews/2026-06-17weekly0.7 https://inferencebench.io/providers/runpod/2026-06-17weekly0.7 https://inferencebench.io/providers/runpod/reviews/2026-06-17weekly0.7 https://inferencebench.io/providers/sambanova/2026-06-17weekly0.7 https://inferencebench.io/providers/sambanova/reviews/2026-06-17weekly0.7 https://inferencebench.io/providers/tensordock/2026-06-17weekly0.7 https://inferencebench.io/providers/tensordock/reviews/2026-06-17weekly0.7 https://inferencebench.io/providers/together-ai/2026-06-17weekly0.7 https://inferencebench.io/providers/together-ai/reviews/2026-06-17weekly0.7 https://inferencebench.io/providers/vast-ai/2026-06-17weekly0.7 https://inferencebench.io/providers/vast-ai/reviews/2026-06-17weekly0.7 https://inferencebench.io/safety/2026-06-17monthly0.3 https://inferencebench.io/status/2026-06-17weekly0.5 https://inferencebench.io/support/2026-06-17weekly0.5 https://inferencebench.io/terms/2026-06-17monthly0.3 https://inferencebench.io/use-case/2026-06-17weekly0.7 https://inferencebench.io/use-case/chatbot/2026-06-17weekly0.7 https://inferencebench.io/use-case/code-generation/2026-06-17weekly0.7 https://inferencebench.io/use-case/content-generation/2026-06-17weekly0.7 https://inferencebench.io/use-case/document-analysis/2026-06-17weekly0.7 https://inferencebench.io/use-case/real-time-translation/2026-06-17weekly0.7 https://inferencebench.io/vs/aws-vs-azure/2026-06-17weekly0.5 https://inferencebench.io/vs/aws-vs-coreweave/2026-06-17weekly0.5 https://inferencebench.io/vs/aws-vs-fluidstack/2026-06-17weekly0.5 https://inferencebench.io/vs/aws-vs-gcp/2026-06-17weekly0.5 https://inferencebench.io/vs/aws-vs-lambda/2026-06-17weekly0.5 https://inferencebench.io/vs/aws-vs-runpod/2026-06-17weekly0.5 https://inferencebench.io/vs/aws-vs-tensordock/2026-06-17weekly0.5 https://inferencebench.io/vs/aws-vs-vast-ai/2026-06-17weekly0.5 https://inferencebench.io/vs/azure-vs-aws/2026-06-17weekly0.5 https://inferencebench.io/vs/azure-vs-coreweave/2026-06-17weekly0.5 https://inferencebench.io/vs/azure-vs-fluidstack/2026-06-17weekly0.5 https://inferencebench.io/vs/azure-vs-gcp/2026-06-17weekly0.5 https://inferencebench.io/vs/azure-vs-lambda/2026-06-17weekly0.5 https://inferencebench.io/vs/azure-vs-runpod/2026-06-17weekly0.5 https://inferencebench.io/vs/azure-vs-tensordock/2026-06-17weekly0.5 https://inferencebench.io/vs/azure-vs-vast-ai/2026-06-17weekly0.5 https://inferencebench.io/vs/coreweave-vs-aws/2026-06-17weekly0.5 https://inferencebench.io/vs/coreweave-vs-azure/2026-06-17weekly0.5 https://inferencebench.io/vs/coreweave-vs-fluidstack/2026-06-17weekly0.5 https://inferencebench.io/vs/coreweave-vs-gcp/2026-06-17weekly0.5 https://inferencebench.io/vs/coreweave-vs-lambda/2026-06-17weekly0.5 https://inferencebench.io/vs/coreweave-vs-runpod/2026-06-17weekly0.5 https://inferencebench.io/vs/coreweave-vs-tensordock/2026-06-17weekly0.5 https://inferencebench.io/vs/coreweave-vs-vast-ai/2026-06-17weekly0.5 https://inferencebench.io/vs/fluidstack-vs-aws/2026-06-17weekly0.5 https://inferencebench.io/vs/fluidstack-vs-azure/2026-06-17weekly0.5 https://inferencebench.io/vs/fluidstack-vs-coreweave/2026-06-17weekly0.5 https://inferencebench.io/vs/fluidstack-vs-gcp/2026-06-17weekly0.5 https://inferencebench.io/vs/fluidstack-vs-lambda/2026-06-17weekly0.5 https://inferencebench.io/vs/fluidstack-vs-runpod/2026-06-17weekly0.5 https://inferencebench.io/vs/fluidstack-vs-tensordock/2026-06-17weekly0.5 https://inferencebench.io/vs/fluidstack-vs-vast-ai/2026-06-17weekly0.5 https://inferencebench.io/vs/gcp-vs-aws/2026-06-17weekly0.5 https://inferencebench.io/vs/gcp-vs-azure/2026-06-17weekly0.5 https://inferencebench.io/vs/gcp-vs-coreweave/2026-06-17weekly0.5 https://inferencebench.io/vs/gcp-vs-fluidstack/2026-06-17weekly0.5 https://inferencebench.io/vs/gcp-vs-lambda/2026-06-17weekly0.5 https://inferencebench.io/vs/gcp-vs-runpod/2026-06-17weekly0.5 https://inferencebench.io/vs/gcp-vs-tensordock/2026-06-17weekly0.5 https://inferencebench.io/vs/gcp-vs-vast-ai/2026-06-17weekly0.5 https://inferencebench.io/vs/lambda-vs-aws/2026-06-17weekly0.5 https://inferencebench.io/vs/lambda-vs-azure/2026-06-17weekly0.5 https://inferencebench.io/vs/lambda-vs-coreweave/2026-06-17weekly0.5 https://inferencebench.io/vs/lambda-vs-fluidstack/2026-06-17weekly0.5 https://inferencebench.io/vs/lambda-vs-gcp/2026-06-17weekly0.5 https://inferencebench.io/vs/lambda-vs-runpod/2026-06-17weekly0.5 https://inferencebench.io/vs/lambda-vs-tensordock/2026-06-17weekly0.5 https://inferencebench.io/vs/lambda-vs-vast-ai/2026-06-17weekly0.5 https://inferencebench.io/vs/runpod-vs-aws/2026-06-17weekly0.5 https://inferencebench.io/vs/runpod-vs-azure/2026-06-17weekly0.5 https://inferencebench.io/vs/runpod-vs-coreweave/2026-06-17weekly0.5 https://inferencebench.io/vs/runpod-vs-fluidstack/2026-06-17weekly0.5 https://inferencebench.io/vs/runpod-vs-gcp/2026-06-17weekly0.5 https://inferencebench.io/vs/runpod-vs-lambda/2026-06-17weekly0.5 https://inferencebench.io/vs/runpod-vs-tensordock/2026-06-17weekly0.5 https://inferencebench.io/vs/runpod-vs-vast-ai/2026-06-17weekly0.5 https://inferencebench.io/vs/tensordock-vs-aws/2026-06-17weekly0.5 https://inferencebench.io/vs/tensordock-vs-azure/2026-06-17weekly0.5 https://inferencebench.io/vs/tensordock-vs-coreweave/2026-06-17weekly0.5 https://inferencebench.io/vs/tensordock-vs-fluidstack/2026-06-17weekly0.5 https://inferencebench.io/vs/tensordock-vs-gcp/2026-06-17weekly0.5 https://inferencebench.io/vs/tensordock-vs-lambda/2026-06-17weekly0.5 https://inferencebench.io/vs/tensordock-vs-runpod/2026-06-17weekly0.5 https://inferencebench.io/vs/tensordock-vs-vast-ai/2026-06-17weekly0.5 https://inferencebench.io/vs/vast-ai-vs-aws/2026-06-17weekly0.5 https://inferencebench.io/vs/vast-ai-vs-azure/2026-06-17weekly0.5 https://inferencebench.io/vs/vast-ai-vs-coreweave/2026-06-17weekly0.5 https://inferencebench.io/vs/vast-ai-vs-fluidstack/2026-06-17weekly0.5 https://inferencebench.io/vs/vast-ai-vs-gcp/2026-06-17weekly0.5 https://inferencebench.io/vs/vast-ai-vs-lambda/2026-06-17weekly0.5 https://inferencebench.io/vs/vast-ai-vs-runpod/2026-06-17weekly0.5 https://inferencebench.io/vs/vast-ai-vs-tensordock/2026-06-17weekly0.5 https://inferencebench.io/workload-matcher/2026-06-17weekly0.9 https://inferencebench.io/workload-matcher/history/2026-06-17weekly0.5 https://inferencebench.io/workload-matcher/pricing/2026-06-17weekly0.5