Skip to content

Qwen 2.5 72B vs Mistral Large 2

Alibaba
Qwen 2.5 72B

Alibaba · 72.7B params · Quality: 84

Mistral
Mistral Large 2

Mistral AI · 123B params · Quality: 82

Architecture Comparison

SpecQwen 2.5 72BMistral Large 2
TypeDENSEDENSE
Total Parameters72.7B123B
Active Parameters72.7B123B
Layers8088
Hidden Dimension8,19212,288
Attention Heads6496
KV Heads88
Context Length131,072131,072
Precision (default)BF16BF16

Memory Requirements

PrecisionQwen 2.5 72BMistral Large 2
BF16 Weights145.4 GB246.0 GB
FP8 Weights72.7 GB123.0 GB
INT4 Weights36.4 GB61.5 GB
KV-Cache / Token327680 B360448 B
Activation Estimate2.50 GB3.50 GB

Minimum GPUs Needed (BF16)

H100 SXM3 GPUs4 GPUs
L40S4 GPUs7 GPUs

Quality Benchmarks

BenchmarkQwen 2.5 72BMistral Large 2
Overall8482
MMLU85.384.0
HumanEval56.053.0
GSM8K91.691.2
MT-Bench86.084.0

Qwen 2.5 72B

MMLU
85.3
HumanEval
56.0
GSM8K
91.6
MT-Bench
86.0

Mistral Large 2

MMLU
84.0
HumanEval
53.0
GSM8K
91.2
MT-Bench
84.0

Capabilities

FeatureQwen 2.5 72BMistral Large 2
Tool Use✓ Yes✓ Yes
Vision✗ No✗ No
Code✓ Yes✓ Yes
Math✓ Yes✓ Yes
Reasoning✗ No✗ No
Multilingual✓ Yes✓ Yes
Structured Output✓ Yes✓ Yes

API Pricing Comparison

Cheapest Output (Qwen 2.5 72B)

$0.90/M

Input: $0.90/M

Cheapest Output (Mistral Large 2)

$2.50/M

Input: $2.50/M

ProviderQwen 2.5 72B In $/MOut $/MMistral Large 2 In $/MOut $/M
together$0.90$0.90$2.50$2.50
fireworks$0.90$0.90
mistral$2.00$6.00

Recommendation Summary

  • Qwen 2.5 72B scores higher on overall quality (84 vs 82).
  • Qwen 2.5 72B is cheaper per output token ($0.90/M vs $2.50/M).
  • Qwen 2.5 72B has a smaller memory footprint (145.4 GB vs 246.0 GB BF16), making it easier to deploy on fewer GPUs.
  • Qwen 2.5 72B is stronger at code generation (HumanEval: 56.0 vs 53.0).
  • Qwen 2.5 72B is better at math reasoning (GSM8K: 91.6 vs 91.2).

Compare Other Models