Model comparison

Mistral Large 3 vs Qwen3-4B

Mistral Large 3 is the stronger model overall, scoring 39.1 to 31.9 on the Noometry Index.

Last verified October 10, 2026. 1 shared benchmarks.

Mistral Large 3

Mistral AI

39.1

Rank #176 Confirmed

Qwen3-4B

Alibaba (Qwen)

31.9

Rank #264 Confirmed

Summary

They share 1 benchmark with published results for both. Mistral Large 3 scores higher in 2 categories and Qwen3-4B in 1 category; 3 gaps are clear of the uncertainty.
The widest gap is in math, where Mistral Large 3 leads 38.7 to 29.7.
The biggest single-benchmark swing is Vectara Hallucination Rate: 14.5% for Mistral Large 3 and 5.7% for Qwen3-4B.

Side by side

Mistral Large 3 and Qwen3-4B specifications
	Mistral Large 3	Qwen3-4B
Provider	Mistral AI	Alibaba (Qwen)
Noometry Index	39.1	31.9
Released	2025-12-02	2025-04-29
Weights	Open	Open
Context window	262K	—
Max output	8K	—
Input $ / M tokens	$0.25	—
Output $ / M tokens	$0.75	—
Results tracked	24	6

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

Category by category

Coding Not comparable

Mistral Large 3: 34.4 (#237), Qwen3-4B: —

Coding benchmarks
Benchmark	Mistral Large 3	Qwen3-4B
LMArena WebDev	1230	—
LMArena Coding	1448	—

Agentic & Tool Use Not comparable

Mistral Large 3: —, Qwen3-4B: 27.6 (#100)

Agentic & Tool Use benchmarks
Benchmark	Mistral Large 3	Qwen3-4B
Berkeley Function Calling Leaderboard	—	35.7%

Reasoning Qwen3-4B leads

Mistral Large 3: 15.2 (#319), Qwen3-4B: 19.2 (#268)

Reasoning benchmarks
Benchmark	Mistral Large 3	Qwen3-4B
Kagi LLM Benchmark	50.9%	—
NYT Connections (extended)	7.5%	—
Chess Puzzles	—	4%
Thematic Generalization	23%	—
LMArena Hard Prompts	1429	—

Math Mistral Large 3 leads

Mistral Large 3: 38.7 (#129), Qwen3-4B: 29.7 (#240)

Math benchmarks
Benchmark	Mistral Large 3	Qwen3-4B
MathArena Final-Answer Competitions	—	38.5%
OTIS Mock AIME 2024-2025	—	52.2%
LMArena Math	1414	—

Knowledge Mistral Large 3 leads

Mistral Large 3: 36.0 (#177), Qwen3-4B: 33.0 (#208)

Knowledge benchmarks
Benchmark	Mistral Large 3	Qwen3-4B
Vectara Hallucination Rate	14.5%	5.7%
GPQA Diamond	—	52.3%
LMArena Expert	1421	—

Multimodal Not comparable

Mistral Large 3: 38.2 (#66), Qwen3-4B: —

Multimodal benchmarks
Benchmark	Mistral Large 3	Qwen3-4B
LMArena Vision	1221	—

Multilingual Not comparable

Mistral Large 3: 52.5 (#84), Qwen3-4B: —

Multilingual benchmarks
Benchmark	Mistral Large 3	Qwen3-4B
LMArena Non-English	1413	—
LMArena Chinese	1447	—
LMArena French	1455	—
LMArena German	1437	—
LMArena Japanese	1394	—
LMArena Korean	1384	—
LMArena Russian	1411	—
LMArena Spanish	1440	—

Instruction Following Not comparable

Mistral Large 3: 74.0 (#108), Qwen3-4B: —

Instruction Following benchmarks
Benchmark	Mistral Large 3	Qwen3-4B
LMArena Instruction Following	1403	—

Long Context Not comparable

Mistral Large 3: 43.1 (#105), Qwen3-4B: —

Long Context benchmarks
Benchmark	Mistral Large 3	Qwen3-4B
LMArena Longer Query	1413	—

Writing & Preference Not comparable

Mistral Large 3: 60.0 (#101), Qwen3-4B: —

Writing & Preference benchmarks
Benchmark	Mistral Large 3	Qwen3-4B
LMArena Text	1428	—
LMArena Creative Writing	1386	—
EQ-Bench Creative Writing	1412	—
LMArena Multi-Turn	1429	—

Frequently asked questions

Is Mistral Large 3 better than Qwen3-4B?