Noometry

Model comparison

Mistral Small vs Qwen1.5-14B

Mistral Small and Qwen1.5-14B score almost the same on the Noometry Index (33.1 vs 32.1), so choose on price, context window or the category you care about most.

Last verified . 17 shared benchmarks.

Mistral Small Mistral AI

33.1

Rank #238 Confirmed

Qwen1.5-14B Alibaba (Qwen)

32.1

Rank #250 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Mistral Small scores higher in 6 categories and Qwen1.5-14B in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Mistral Small leads 52.6 to 33.7.

Side by side

Mistral SmallQwen1.5-14B
ProviderMistral AIAlibaba (Qwen)
Noometry Index33.132.1
Released2024-02-262024-02-04
WeightsOpenOpen
Context window256K—
Max output256K—
Input $ / M tokens$0.15—
Output $ / M tokens$0.60—
Results tracked3917

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

Category by category

Coding Mistral Small leads

Mistral Small: 33.5 (#242), Qwen1.5-14B: 32.5 (#259)

BenchmarkMistral SmallQwen1.5-14B
LMArena Coding13631138
SciCode26.5%—
BigCodeBench Instruct36.1%—
LiveBench Coding36.2%—
BigCodeBench Complete46.6%—
ALE-Bench497.62—

Agentic & Tool Use Not comparable

Mistral Small: 27.9 (#87), Qwen1.5-14B: —

BenchmarkMistral SmallQwen1.5-14B
Berkeley Function Calling Leaderboard37.1%—

Reasoning Qwen1.5-14B leads

Mistral Small: 19.3 (#238), Qwen1.5-14B: 20.5 (#217)

BenchmarkMistral SmallQwen1.5-14B
LMArena Hard Prompts13361113
Kagi LLM Benchmark37.8%—
CritPt0%—
LiveBench Reasoning44.8%—
DTBench70.9%—
LiveBench Data Analysis53.7%—
LMCA20.6%—
LiveBench44%—

Math Qwen1.5-14B leads

Mistral Small: 15.4 (#287), Qwen1.5-14B: 29.9 (#214)

BenchmarkMistral SmallQwen1.5-14B
LMArena Math13411125
OTIS Mock AIME 2024-20255.8%—
LiveBench Math39.9%—
MATH Level 546.8%—

Knowledge Mistral Small leads

Mistral Small: 30.9 (#214), Qwen1.5-14B: 29.3 (#230)

BenchmarkMistral SmallQwen1.5-14B
LMArena Expert12931094
MMLU68.7%68.6%
GPQA Diamond47.5%—
Vectara Hallucination Rate5.1%—

Multimodal Not comparable

Mistral Small: 32.9 (#91), Qwen1.5-14B: —

BenchmarkMistral SmallQwen1.5-14B
LMArena Vision1142—

Multilingual Mistral Small leads

Mistral Small: 45.7 (#164), Qwen1.5-14B: 30.8 (#257)

BenchmarkMistral SmallQwen1.5-14B
LMArena Non-English13151095
LMArena Chinese13421147
LMArena French13371115
LMArena German13411043
LMArena Japanese12751019
LMArena Russian13241046
LMArena Spanish13461085
LMArena Korean1260—

Instruction Following Mistral Small leads

Mistral Small: 66.6 (#204), Qwen1.5-14B: 57.1 (#266)

BenchmarkMistral SmallQwen1.5-14B
LMArena Instruction Following13101102
LiveBench Instruction Following63.7%—

Long Context Mistral Small leads

Mistral Small: 40.4 (#151), Qwen1.5-14B: 33.7 (#252)

BenchmarkMistral SmallQwen1.5-14B
LMArena Longer Query13271113

Writing & Preference Mistral Small leads

Mistral Small: 52.6 (#165), Qwen1.5-14B: 33.7 (#270)

BenchmarkMistral SmallQwen1.5-14B
LMArena Text13381128
LMArena Creative Writing13041091
LMArena Multi-Turn13441110
LiveBench Language30.5%—

Frequently asked questions

Is Mistral Small better than Qwen1.5-14B?

Mistral Small and Qwen1.5-14B score almost the same on the Noometry Index (33.1 vs 32.1), so choose on price, context window or the category you care about most.

Is Mistral Small or Qwen1.5-14B better for coding?

Mistral Small scores higher on coding benchmarks: 33.5 versus 32.5 in the Noometry coding category.

How many benchmarks do Mistral Small and Qwen1.5-14B share?

17 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Qwen1.5-14B has 17.

Related comparisons

Go deeper