Model comparison

Mistral Medium 3.5 vs Qwen3-4B

Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 31.9 on the Noometry Index.

Last verified October 12, 2026. 0 shared benchmarks.

Mistral Medium 3.5

Mistral AI

40.2

Rank #152 Confirmed

Qwen3-4B

Alibaba (Qwen)

31.9

Rank #264 Confirmed

Summary

The widest gap is in math, where Mistral Medium 3.5 leads 39.1 to 29.7.

Side by side

Mistral Medium 3.5 and Qwen3-4B specifications
	Mistral Medium 3.5	Qwen3-4B
Provider	Mistral AI	Alibaba (Qwen)
Noometry Index	40.2	31.9
Released	—	2025-04-29
Weights	Open	Open
Context window	262K	—
Max output	210K	—
Input $ / M tokens	$1.50	—
Output $ / M tokens	$7.50	—
Results tracked	22	6

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

Category by category

Coding Not comparable

Mistral Medium 3.5: 36.0 (#213), Qwen3-4B: —

Coding benchmarks
Benchmark	Mistral Medium 3.5	Qwen3-4B
LMArena WebDev	1264	—
LMArena Coding	1461	—

Agentic & Tool Use Not comparable

Mistral Medium 3.5: —, Qwen3-4B: 27.6 (#100)

Agentic & Tool Use benchmarks
Benchmark	Mistral Medium 3.5	Qwen3-4B
Berkeley Function Calling Leaderboard	—	35.7%

Reasoning Qwen3-4B leads

Mistral Medium 3.5: 17.3 (#295), Qwen3-4B: 19.2 (#268)

Reasoning benchmarks
Benchmark	Mistral Medium 3.5	Qwen3-4B
Kagi LLM Benchmark	41.4%	—
NYT Connections (extended)	12.9%	—
Chess Puzzles	—	4%
LMArena Hard Prompts	1436	—
Epoch Capabilities Index	141.35	—

Math Mistral Medium 3.5 leads

Mistral Medium 3.5: 39.1 (#113), Qwen3-4B: 29.7 (#240)

Math benchmarks
Benchmark	Mistral Medium 3.5	Qwen3-4B
MathArena Final-Answer Competitions	—	38.5%
OTIS Mock AIME 2024-2025	—	52.2%
LMArena Math	1431	—

Knowledge Mistral Medium 3.5 leads

Mistral Medium 3.5: 40.0 (#126), Qwen3-4B: 33.0 (#208)

Knowledge benchmarks
Benchmark	Mistral Medium 3.5	Qwen3-4B
GPQA Diamond	—	52.3%
Vectara Hallucination Rate	—	5.7%
LMArena Expert	1432	—

Multimodal Not comparable

Mistral Medium 3.5: 38.3 (#65), Qwen3-4B: —

Multimodal benchmarks
Benchmark	Mistral Medium 3.5	Qwen3-4B
LMArena Vision	1223	—

Multilingual Not comparable

Mistral Medium 3.5: 51.9 (#100), Qwen3-4B: —

Multilingual benchmarks
Benchmark	Mistral Medium 3.5	Qwen3-4B
LMArena Non-English	1404	—
LMArena Chinese	1442	—
LMArena French	1448	—
LMArena German	1451	—
LMArena Korean	1385	—
LMArena Russian	1395	—
LMArena Spanish	1409	—

Instruction Following Not comparable

Mistral Medium 3.5: 74.6 (#90), Qwen3-4B: —

Instruction Following benchmarks
Benchmark	Mistral Medium 3.5	Qwen3-4B
LMArena Instruction Following	1415	—

Long Context Not comparable

Mistral Medium 3.5: 43.2 (#103), Qwen3-4B: —

Long Context benchmarks
Benchmark	Mistral Medium 3.5	Qwen3-4B
LMArena Longer Query	1415	—

Writing & Preference Not comparable

Mistral Medium 3.5: 58.5 (#117), Qwen3-4B: —

Writing & Preference benchmarks
Benchmark	Mistral Medium 3.5	Qwen3-4B
LMArena Text	1421	—
LMArena Creative Writing	1374	—
EQ-Bench 4	993	—
LMArena Multi-Turn	1423	—

Frequently asked questions

Is Mistral Medium 3.5 better than Qwen3-4B?