Model comparison
Mistral Small vs Qwen3-4B
Mistral Small is the stronger model overall, scoring 33.4 to 31.9 on the Noometry Index.
Last verified . 4 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. Mistral Small scores higher in 2 categories and Qwen3-4B in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3-4B leads 29.7 to 16.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 5.8% for Mistral Small and 52.2% for Qwen3-4B.
Side by side
| Mistral Small | Qwen3-4B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 33.4 | 31.9 |
| Released | 2024-02-26 | 2025-04-29 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 256K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 39 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mistral Small: 34.0 (#247), Qwen3-4B: —
| Benchmark | Mistral Small | Qwen3-4B |
|---|---|---|
| SciCode | 26.5% | — |
| BigCodeBench Instruct | 36.1% | — |
| LiveBench Coding | 36.2% | — |
| LMArena Coding | 1362 | — |
| BigCodeBench Complete | 46.6% | — |
| ALE-Bench | 497.62 | — |
Agentic & Tool Use Too close to call
Mistral Small: 28.1 (#93), Qwen3-4B: 27.6 (#100)
| Benchmark | Mistral Small | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | 35.7% |
Reasoning Too close to call
Mistral Small: 19.8 (#250), Qwen3-4B: 19.2 (#268)
| Benchmark | Mistral Small | Qwen3-4B |
|---|---|---|
| Kagi LLM Benchmark | 37.8% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 4% |
| LiveBench Reasoning | 44.8% | — |
| LMArena Hard Prompts | 1335 | — |
| DTBench | 70.9% | — |
| LiveBench Data Analysis | 53.7% | — |
| LMCA | 20.6% | — |
| LiveBench | 44% | — |
Math Qwen3-4B leads
Mistral Small: 16.4 (#293), Qwen3-4B: 29.7 (#240)
| Benchmark | Mistral Small | Qwen3-4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.8% | 52.2% |
| MathArena Final-Answer Competitions | — | 38.5% |
| LiveBench Math | 39.9% | — |
| LMArena Math | 1341 | — |
| MATH Level 5 | 46.8% | — |
Knowledge Qwen3-4B leads
Mistral Small: 31.0 (#222), Qwen3-4B: 33.0 (#208)
| Benchmark | Mistral Small | Qwen3-4B |
|---|---|---|
| GPQA Diamond | 47.5% | 52.3% |
| Vectara Hallucination Rate | 5.1% | 5.7% |
| LMArena Expert | 1291 | — |
| MMLU | 68.7% | — |
Multimodal Not comparable
Mistral Small: 33.5 (#96), Qwen3-4B: —
| Benchmark | Mistral Small | Qwen3-4B |
|---|---|---|
| LMArena Vision | 1142 | — |
Multilingual Not comparable
Mistral Small: 45.5 (#169), Qwen3-4B: —
| Benchmark | Mistral Small | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1315 | — |
| LMArena Chinese | 1340 | — |
| LMArena French | 1337 | — |
| LMArena German | 1340 | — |
| LMArena Japanese | 1275 | — |
| LMArena Korean | 1259 | — |
| LMArena Russian | 1324 | — |
| LMArena Spanish | 1346 | — |
Instruction Following Not comparable
Mistral Small: 66.4 (#209), Qwen3-4B: —
| Benchmark | Mistral Small | Qwen3-4B |
|---|---|---|
| LiveBench Instruction Following | 63.7% | — |
| LMArena Instruction Following | 1310 | — |
Long Context Not comparable
Mistral Small: 40.4 (#156), Qwen3-4B: —
| Benchmark | Mistral Small | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1327 | — |
Writing & Preference Not comparable
Mistral Small: 52.5 (#171), Qwen3-4B: —
| Benchmark | Mistral Small | Qwen3-4B |
|---|---|---|
| LMArena Text | 1338 | — |
| LMArena Creative Writing | 1305 | — |
| LMArena Multi-Turn | 1344 | — |
| LiveBench Language | 30.5% | — |
Frequently asked questions
Is Mistral Small better than Qwen3-4B?
Mistral Small is the stronger model overall, scoring 33.4 to 31.9 on the Noometry Index.
How many benchmarks do Mistral Small and Qwen3-4B share?
4 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Qwen3-4B has 6.