Model comparison
Pixtral Large vs Qwen Max
Qwen Max is the stronger model overall, scoring 34.7 to 32.2 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- The widest gap is in writing & preference, where Qwen Max leads 47.8 to 32.9.
- Qwen Max is cheaper at $1.60 / $6.40 per million input/output tokens, against $2 / $6 for Pixtral Large.
- Pixtral Large accepts more context: 128K tokens versus 33K.
- Pixtral Large has downloadable open weights; the other is API-only.
Side by side
| Pixtral Large | Qwen Max | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 32.2 | 34.7 |
| Released | 2024-11-01 | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | 128K | 33K |
| Max output | 128K | 8K |
| Input $ / M tokens | $2 | $1.60 |
| Output $ / M tokens | $6 | $6.40 |
| Results tracked | 3 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Pixtral Large: —, Qwen Max: 30.7 (#292)
| Benchmark | Pixtral Large | Qwen Max |
|---|---|---|
| Aider Polyglot | — | 21.8% |
| LMArena Coding | — | 1288 |
Reasoning Qwen Max leads
Pixtral Large: 21.7 (#218), Qwen Max: 25.1 (#151)
| Benchmark | Pixtral Large | Qwen Max |
|---|---|---|
| EnigmaEval | 0.8% | — |
| LMArena Hard Prompts | — | 1269 |
Math Not comparable
Pixtral Large: —, Qwen Max: 22.3 (#276)
| Benchmark | Pixtral Large | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| LMArena Math | — | 1275 |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Not comparable
Pixtral Large: —, Qwen Max: 30.3 (#228)
| Benchmark | Pixtral Large | Qwen Max |
|---|---|---|
| GPQA Diamond | — | 56.1% |
| LMArena Expert | — | 1248 |
Multimodal Not comparable
Pixtral Large: 30.6 (#111), Qwen Max: —
| Benchmark | Pixtral Large | Qwen Max |
|---|---|---|
| LMArena Vision | 1089 | — |
Multilingual Not comparable
Pixtral Large: —, Qwen Max: 41.8 (#202)
| Benchmark | Pixtral Large | Qwen Max |
|---|---|---|
| LMArena Non-English | — | 1263 |
| LMArena Chinese | — | 1254 |
| LMArena French | — | 1330 |
| LMArena German | — | 1254 |
| LMArena Japanese | — | 1205 |
| LMArena Korean | — | 1142 |
| LMArena Russian | — | 1274 |
| LMArena Spanish | — | 1290 |
Instruction Following Not comparable
Pixtral Large: —, Qwen Max: 66.5 (#208)
| Benchmark | Pixtral Large | Qwen Max |
|---|---|---|
| LMArena Instruction Following | — | 1262 |
Long Context Not comparable
Pixtral Large: —, Qwen Max: 39.4 (#180)
| Benchmark | Pixtral Large | Qwen Max |
|---|---|---|
| Fiction.LiveBench | — | 66.7% |
| LMArena Longer Query | — | 1288 |
Writing & Preference Qwen Max leads
Pixtral Large: 32.9 (#278), Qwen Max: 47.8 (#205)
| Benchmark | Pixtral Large | Qwen Max |
|---|---|---|
| LMArena Text | — | 1282 |
| LMArena Creative Writing | — | 1248 |
| EQ-Bench Creative Writing | 988 | — |
| LMArena Multi-Turn | — | 1277 |
Frequently asked questions
Is Pixtral Large better than Qwen Max?
Qwen Max is the stronger model overall, scoring 34.7 to 32.2 on the Noometry Index.
Which is cheaper, Pixtral Large or Qwen Max?
Qwen Max is cheaper. It lists at $1.60 per million input tokens and $6.40 per million output tokens; Pixtral Large lists at $2 and $6.
Which has the bigger context window?
Pixtral Large does, with 128K tokens against 33K.
How many benchmarks do Pixtral Large and Qwen Max share?
0 benchmarks have published results for both models. Pixtral Large has 3 scored results on Noometry and Qwen Max has 23.