Noometry

Model comparison

Mistral Small vs Qwen1.5-32B

Mistral Small is the stronger model overall, scoring 33.4 to 30.5 on the Noometry Index.

Last verified . 21 shared benchmarks.

Mistral Small Mistral AI

33.4

Rank #243 Confirmed

Qwen1.5-32B Alibaba (Qwen)

30.5

Rank #293 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Mistral Small scores higher in 6 categories and Qwen1.5-32B in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Mistral Small leads 52.5 to 34.2.
  • The biggest single-benchmark swing is GPQA Diamond: 47.5% for Mistral Small and 30.7% for Qwen1.5-32B.

Side by side

Mistral SmallQwen1.5-32B
ProviderMistral AIAlibaba (Qwen)
Noometry Index33.430.5
Released2024-02-262024-02-04
WeightsOpenOpen
Context window262K—
Max output256K—
Input $ / M tokens$0.15—
Output $ / M tokens$0.60—
Results tracked3921

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

Category by category

Coding Mistral Small leads

Mistral Small: 34.0 (#247), Qwen1.5-32B: 31.7 (#282)

BenchmarkMistral SmallQwen1.5-32B
BigCodeBench Instruct36.1%32.3%
LMArena Coding13621155
BigCodeBench Complete46.6%42%
SciCode26.5%—
LiveBench Coding36.2%—
ALE-Bench497.62—

Agentic & Tool Use Not comparable

Mistral Small: 28.1 (#93), Qwen1.5-32B: —

BenchmarkMistral SmallQwen1.5-32B
Berkeley Function Calling Leaderboard37.1%—

Reasoning Qwen1.5-32B leads

Mistral Small: 19.8 (#250), Qwen1.5-32B: 21.8 (#212)

BenchmarkMistral SmallQwen1.5-32B
LMArena Hard Prompts13351130
Kagi LLM Benchmark37.8%—
CritPt0%—
LiveBench Reasoning44.8%—
DTBench70.9%—
LiveBench Data Analysis53.7%—
LMCA20.6%—
LiveBench44%—

Math Qwen1.5-32B leads

Mistral Small: 16.4 (#293), Qwen1.5-32B: 33.0 (#207)

BenchmarkMistral SmallQwen1.5-32B
LMArena Math13411155
OTIS Mock AIME 2024-20255.8%—
LiveBench Math39.9%—
MATH Level 546.8%—

Knowledge Mistral Small leads

Mistral Small: 31.0 (#222), Qwen1.5-32B: 13.5 (#296)

BenchmarkMistral SmallQwen1.5-32B
GPQA Diamond47.5%30.7%
LMArena Expert12911126
MMLU68.7%74.4%
Vectara Hallucination Rate5.1%—

Multimodal Not comparable

Mistral Small: 33.5 (#96), Qwen1.5-32B: —

BenchmarkMistral SmallQwen1.5-32B
LMArena Vision1142—

Multilingual Mistral Small leads

Mistral Small: 45.5 (#169), Qwen1.5-32B: 31.4 (#259)

BenchmarkMistral SmallQwen1.5-32B
LMArena Non-English13151106
LMArena Chinese13401177
LMArena French13371101
LMArena German13401058
LMArena Japanese12751027
LMArena Korean12591008
LMArena Russian13241073
LMArena Spanish13461089

Instruction Following Mistral Small leads

Mistral Small: 66.4 (#209), Qwen1.5-32B: 57.7 (#265)

BenchmarkMistral SmallQwen1.5-32B
LMArena Instruction Following13101116
LiveBench Instruction Following63.7%—

Long Context Mistral Small leads

Mistral Small: 40.4 (#156), Qwen1.5-32B: 34.7 (#246)

BenchmarkMistral SmallQwen1.5-32B
LMArena Longer Query13271146

Writing & Preference Mistral Small leads

Mistral Small: 52.5 (#171), Qwen1.5-32B: 34.2 (#271)

BenchmarkMistral SmallQwen1.5-32B
LMArena Text13381137
LMArena Creative Writing13051083
LMArena Multi-Turn13441140
LiveBench Language30.5%—

Frequently asked questions

Is Mistral Small better than Qwen1.5-32B?

Mistral Small is the stronger model overall, scoring 33.4 to 30.5 on the Noometry Index.

Is Mistral Small or Qwen1.5-32B better for coding?

Mistral Small scores higher on coding benchmarks: 34.0 versus 31.7 in the Noometry coding category.

How many benchmarks do Mistral Small and Qwen1.5-32B share?

21 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Qwen1.5-32B has 21.

Related comparisons

Go deeper