Noometry

Model comparison

Mistral Small vs Qwen1.5-72B

Mistral Small is the stronger model overall, scoring 33.4 to 30.8 on the Noometry Index.

Last verified . 20 shared benchmarks.

Mistral Small Mistral AI

33.4

Rank #243 Confirmed

Qwen1.5-72B Alibaba (Qwen)

30.8

Rank #285 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Mistral Small scores higher in 6 categories and Qwen1.5-72B in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Mistral Small leads 31.0 to 11.5.
  • The biggest single-benchmark swing is GPQA Diamond: 47.5% for Mistral Small and 28.8% for Qwen1.5-72B.

Side by side

Mistral SmallQwen1.5-72B
ProviderMistral AIAlibaba (Qwen)
Noometry Index33.430.8
Released2024-02-262024-02-04
WeightsOpenOpen
Context window262K—
Max output256K—
Input $ / M tokens$0.15—
Output $ / M tokens$0.60—
Results tracked3922

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Mistral Small leads

Mistral Small: 34.0 (#247), Qwen1.5-72B: 31.9 (#277)

BenchmarkMistral SmallQwen1.5-72B
BigCodeBench Instruct36.1%33.2%
LMArena Coding13621165
BigCodeBench Complete46.6%40.3%
SciCode26.5%—
LiveBench Coding36.2%—
ALE-Bench497.62—
HumanEval+—59.1%
MBPP+—61.6%

Agentic & Tool Use Not comparable

Mistral Small: 28.1 (#93), Qwen1.5-72B: —

BenchmarkMistral SmallQwen1.5-72B
Berkeley Function Calling Leaderboard37.1%—

Reasoning Qwen1.5-72B leads

Mistral Small: 19.8 (#250), Qwen1.5-72B: 22.2 (#203)

BenchmarkMistral SmallQwen1.5-72B
LMArena Hard Prompts13351148
Kagi LLM Benchmark37.8%—
CritPt0%—
LiveBench Reasoning44.8%—
DTBench70.9%—
LiveBench Data Analysis53.7%—
LMCA20.6%—
LiveBench44%—

Math Qwen1.5-72B leads

Mistral Small: 16.4 (#293), Qwen1.5-72B: 33.2 (#205)

BenchmarkMistral SmallQwen1.5-72B
LMArena Math13411164
OTIS Mock AIME 2024-20255.8%—
LiveBench Math39.9%—
MATH Level 546.8%—

Knowledge Mistral Small leads

Mistral Small: 31.0 (#222), Qwen1.5-72B: 11.5 (#300)

BenchmarkMistral SmallQwen1.5-72B
GPQA Diamond47.5%28.8%
LMArena Expert12911136
Vectara Hallucination Rate5.1%—
MMLU68.7%—

Multimodal Not comparable

Mistral Small: 33.5 (#96), Qwen1.5-72B: —

BenchmarkMistral SmallQwen1.5-72B
LMArena Vision1142—

Multilingual Mistral Small leads

Mistral Small: 45.5 (#169), Qwen1.5-72B: 33.2 (#253)

BenchmarkMistral SmallQwen1.5-72B
LMArena Non-English13151135
LMArena Chinese13401186
LMArena French13371159
LMArena German13401084
LMArena Japanese12751061
LMArena Korean12591050
LMArena Russian13241104
LMArena Spanish13461110

Instruction Following Mistral Small leads

Mistral Small: 66.4 (#209), Qwen1.5-72B: 59.3 (#256)

BenchmarkMistral SmallQwen1.5-72B
LMArena Instruction Following13101141
LiveBench Instruction Following63.7%—

Long Context Mistral Small leads

Mistral Small: 40.4 (#156), Qwen1.5-72B: 35.1 (#243)

BenchmarkMistral SmallQwen1.5-72B
LMArena Longer Query13271157

Writing & Preference Mistral Small leads

Mistral Small: 52.5 (#171), Qwen1.5-72B: 37.3 (#258)

BenchmarkMistral SmallQwen1.5-72B
LMArena Text13381166
LMArena Creative Writing13051137
LMArena Multi-Turn13441160
LiveBench Language30.5%—

Frequently asked questions

Is Mistral Small better than Qwen1.5-72B?

Mistral Small is the stronger model overall, scoring 33.4 to 30.8 on the Noometry Index.

Is Mistral Small or Qwen1.5-72B better for coding?

Mistral Small scores higher on coding benchmarks: 34.0 versus 31.9 in the Noometry coding category.

How many benchmarks do Mistral Small and Qwen1.5-72B share?

20 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Qwen1.5-72B has 22.

Related comparisons

Go deeper