Model comparison
Mistral Small vs Qwen Max
Qwen Max is the stronger model overall, scoring 34.7 to 33.4 on the Noometry Index. Mistral Small costs 11× less per token, which makes it the better buy when Qwen Max's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Mistral Small scores higher in 5 categories and Qwen Max in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen Max leads 22.3 to 16.4.
- The biggest single-benchmark swing is MATH Level 5: 46.8% for Mistral Small and 67.2% for Qwen Max.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- Mistral Small accepts more context: 262K tokens versus 33K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| Mistral Small | Qwen Max | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 33.4 | 34.7 |
| Released | 2024-02-26 | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | 262K | 33K |
| Max output | 256K | 8K |
| Input $ / M tokens | $0.15 | $1.60 |
| Output $ / M tokens | $0.60 | $6.40 |
| Results tracked | 39 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small leads
Mistral Small: 34.0 (#247), Qwen Max: 30.7 (#292)
| Benchmark | Mistral Small | Qwen Max |
|---|---|---|
| LMArena Coding | 1362 | 1288 |
| Aider Polyglot | — | 21.8% |
| SciCode | 26.5% | — |
| BigCodeBench Instruct | 36.1% | — |
| LiveBench Coding | 36.2% | — |
| BigCodeBench Complete | 46.6% | — |
| ALE-Bench | 497.62 | — |
Agentic & Tool Use Not comparable
Mistral Small: 28.1 (#93), Qwen Max: —
| Benchmark | Mistral Small | Qwen Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | — |
Reasoning Qwen Max leads
Mistral Small: 19.8 (#250), Qwen Max: 25.1 (#151)
| Benchmark | Mistral Small | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1335 | 1269 |
| Kagi LLM Benchmark | 37.8% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 44.8% | — |
| DTBench | 70.9% | — |
| LiveBench Data Analysis | 53.7% | — |
| LMCA | 20.6% | — |
| LiveBench | 44% | — |
Math Qwen Max leads
Mistral Small: 16.4 (#293), Qwen Max: 22.3 (#276)
| Benchmark | Mistral Small | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.8% | 16.1% |
| LMArena Math | 1341 | 1275 |
| MATH Level 5 | 46.8% | 67.2% |
| LiveBench Math | 39.9% | — |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Too close to call
Mistral Small: 31.0 (#222), Qwen Max: 30.3 (#228)
| Benchmark | Mistral Small | Qwen Max |
|---|---|---|
| GPQA Diamond | 47.5% | 56.1% |
| LMArena Expert | 1291 | 1248 |
| Vectara Hallucination Rate | 5.1% | — |
| MMLU | 68.7% | — |
Multimodal Not comparable
Mistral Small: 33.5 (#96), Qwen Max: —
| Benchmark | Mistral Small | Qwen Max |
|---|---|---|
| LMArena Vision | 1142 | — |
Multilingual Mistral Small leads
Mistral Small: 45.5 (#169), Qwen Max: 41.8 (#202)
| Benchmark | Mistral Small | Qwen Max |
|---|---|---|
| LMArena Non-English | 1315 | 1263 |
| LMArena Chinese | 1340 | 1254 |
| LMArena French | 1337 | 1330 |
| LMArena German | 1340 | 1254 |
| LMArena Japanese | 1275 | 1205 |
| LMArena Korean | 1259 | 1142 |
| LMArena Russian | 1324 | 1274 |
| LMArena Spanish | 1346 | 1290 |
Instruction Following Too close to call
Mistral Small: 66.4 (#209), Qwen Max: 66.5 (#208)
| Benchmark | Mistral Small | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1310 | 1262 |
| LiveBench Instruction Following | 63.7% | — |
Long Context Too close to call
Mistral Small: 40.4 (#156), Qwen Max: 39.4 (#180)
| Benchmark | Mistral Small | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1327 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Mistral Small leads
Mistral Small: 52.5 (#171), Qwen Max: 47.8 (#205)
| Benchmark | Mistral Small | Qwen Max |
|---|---|---|
| LMArena Text | 1338 | 1282 |
| LMArena Creative Writing | 1305 | 1248 |
| LMArena Multi-Turn | 1344 | 1277 |
| LiveBench Language | 30.5% | — |
Frequently asked questions
Is Mistral Small better than Qwen Max?
Qwen Max is the stronger model overall, scoring 34.7 to 33.4 on the Noometry Index. Mistral Small costs 11× less per token, which makes it the better buy when Qwen Max's lead doesn't matter for your workload.
Which is cheaper, Mistral Small or Qwen Max?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen Max lists at $1.60 and $6.40.
Is Mistral Small or Qwen Max better for coding?
Mistral Small scores higher on coding benchmarks: 34.0 versus 30.7 in the Noometry coding category.
Which has the bigger context window?
Mistral Small does, with 262K tokens against 33K.
How many benchmarks do Mistral Small and Qwen Max share?
20 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Qwen Max has 23.