Noometry

Model comparison

Mistral Large 3 vs Qwen2.5 32B Instruct

Mistral Large 3 is the stronger model overall, scoring 39.1 to 30.1 on the Noometry Index.

Last verified . 0 shared benchmarks.

Mistral Large 3 Mistral AI

39.1

Rank #176 Confirmed

Qwen2.5 32B Instruct Alibaba (Qwen)

30.1

Rank #297 Confirmed

Summary

  • The widest gap is in math, where Mistral Large 3 leads 38.7 to 16.2.
  • Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.70 / $2.80 for Qwen2.5 32B Instruct.
  • Mistral Large 3 accepts more context: 262K tokens versus 131K.

Side by side

Mistral Large 3Qwen2.5 32B Instruct
ProviderMistral AIAlibaba (Qwen)
Noometry Index39.130.1
Released2025-12-022024-09
WeightsOpenOpen
Context window262K131K
Max output8K8K
Input $ / M tokens$0.25$0.70
Output $ / M tokens$0.75$2.80
Results tracked247

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

Category by category

Coding Qwen2.5 32B Instruct leads

Mistral Large 3: 34.4 (#237), Qwen2.5 32B Instruct: 38.7 (#169)

BenchmarkMistral Large 3Qwen2.5 32B Instruct
LMArena WebDev1230—
BigCodeBench Instruct—45%
LMArena Coding1448—
BigCodeBench Complete—52.3%

Reasoning Qwen2.5 32B Instruct leads

Mistral Large 3: 15.2 (#319), Qwen2.5 32B Instruct: 19.2 (#266)

BenchmarkMistral Large 3Qwen2.5 32B Instruct
Kagi LLM Benchmark50.9%—
NYT Connections (extended)7.5%—
Chess Puzzles—0%
Thematic Generalization23%—
LMArena Hard Prompts1429—
Epoch Capabilities Index—128.52

Math Mistral Large 3 leads

Mistral Large 3: 38.7 (#129), Qwen2.5 32B Instruct: 16.2 (#296)

BenchmarkMistral Large 3Qwen2.5 32B Instruct
OTIS Mock AIME 2024-2025—7.4%
LMArena Math1414—
MATH Level 5—56.1%

Knowledge Mistral Large 3 leads

Mistral Large 3: 36.0 (#177), Qwen2.5 32B Instruct: 24.9 (#266)

BenchmarkMistral Large 3Qwen2.5 32B Instruct
GPQA Diamond—46.1%
Vectara Hallucination Rate14.5%—
LMArena Expert1421—

Multimodal Not comparable

Mistral Large 3: 38.2 (#66), Qwen2.5 32B Instruct: —

BenchmarkMistral Large 3Qwen2.5 32B Instruct
LMArena Vision1221—

Multilingual Not comparable

Mistral Large 3: 52.5 (#84), Qwen2.5 32B Instruct: —

BenchmarkMistral Large 3Qwen2.5 32B Instruct
LMArena Non-English1413—
LMArena Chinese1447—
LMArena French1455—
LMArena German1437—
LMArena Japanese1394—
LMArena Korean1384—
LMArena Russian1411—
LMArena Spanish1440—

Instruction Following Not comparable

Mistral Large 3: 74.0 (#108), Qwen2.5 32B Instruct: —

BenchmarkMistral Large 3Qwen2.5 32B Instruct
LMArena Instruction Following1403—

Long Context Not comparable

Mistral Large 3: 43.1 (#105), Qwen2.5 32B Instruct: —

BenchmarkMistral Large 3Qwen2.5 32B Instruct
LMArena Longer Query1413—

Writing & Preference Not comparable

Mistral Large 3: 60.0 (#101), Qwen2.5 32B Instruct: —

BenchmarkMistral Large 3Qwen2.5 32B Instruct
LMArena Text1428—
LMArena Creative Writing1386—
EQ-Bench Creative Writing1412—
LMArena Multi-Turn1429—

Frequently asked questions

Is Mistral Large 3 better than Qwen2.5 32B Instruct?

Mistral Large 3 is the stronger model overall, scoring 39.1 to 30.1 on the Noometry Index.

Which is cheaper, Mistral Large 3 or Qwen2.5 32B Instruct?

Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Qwen2.5 32B Instruct lists at $0.70 and $2.80.

Is Mistral Large 3 or Qwen2.5 32B Instruct better for coding?

Qwen2.5 32B Instruct scores higher on coding benchmarks: 38.7 versus 34.4 in the Noometry coding category.

Which has the bigger context window?

Mistral Large 3 does, with 262K tokens against 131K.

How many benchmarks do Mistral Large 3 and Qwen2.5 32B Instruct share?

0 benchmarks have published results for both models. Mistral Large 3 has 24 scored results on Noometry and Qwen2.5 32B Instruct has 7.

Related comparisons

Go deeper