Model comparison
Mistral Large vs Qwen3.5 Max Preview
Qwen3.5 Max Preview is the stronger model overall, scoring 45.3 to 31.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Mistral Large scores higher in 0 categories and Qwen3.5 Max Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 Max Preview leads 66.0 to 40.7.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Mistral Large | Qwen3.5 Max Preview | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.9 | 45.3 |
| Released | 2024-02-26 | — |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 51 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 Max Preview leads
Mistral Large: 34.3 (#240), Qwen3.5 Max Preview: 44.0 (#77)
| Benchmark | Mistral Large | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Coding | 1277 | 1487 |
| SciCode | 36.2% | — |
| BigCodeBench Instruct | 30% | — |
| LiveBench Coding | 47.1% | — |
| BigCodeBench Complete | 38.3% | — |
| ALE-Bench | 264.7 | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |
Agentic & Tool Use Not comparable
Mistral Large: 28.6 (#89), Qwen3.5 Max Preview: —
| Benchmark | Mistral Large | Qwen3.5 Max Preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |
Reasoning Qwen3.5 Max Preview leads
Mistral Large: 15.8 (#310), Qwen3.5 Max Preview: 30.8 (#84)
| Benchmark | Mistral Large | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1483 |
| SimpleBench | 22.5% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 43.5% | — |
| DTBench | 65.1% | — |
| LiveBench Data Analysis | 50.1% | — |
| LMCA | 16.7% | — |
| Epoch Capabilities Index | 128.52 | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |
Math Qwen3.5 Max Preview leads
Mistral Large: 18.2 (#291), Qwen3.5 Max Preview: 40.1 (#94)
| Benchmark | Mistral Large | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Math | 1262 | 1474 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Qwen3.5 Max Preview leads
Mistral Large: 30.1 (#230), Qwen3.5 Max Preview: 41.8 (#107)
| Benchmark | Mistral Large | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Expert | 1232 | 1489 |
| GPQA Diamond | 51.3% | — |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |
Multilingual Qwen3.5 Max Preview leads
Mistral Large: 40.0 (#219), Qwen3.5 Max Preview: 56.2 (#22)
| Benchmark | Mistral Large | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Non-English | 1237 | 1465 |
| LMArena Chinese | 1240 | 1534 |
| LMArena French | 1325 | 1484 |
| LMArena German | 1254 | 1487 |
| LMArena Japanese | 1188 | 1495 |
| LMArena Korean | 1202 | 1438 |
| LMArena Russian | 1257 | 1471 |
| LMArena Spanish | 1268 | 1470 |
Instruction Following Qwen3.5 Max Preview leads
Mistral Large: 67.9 (#191), Qwen3.5 Max Preview: 77.0 (#31)
| Benchmark | Mistral Large | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1249 | 1467 |
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
Long Context Qwen3.5 Max Preview leads
Mistral Large: 38.3 (#199), Qwen3.5 Max Preview: 45.2 (#45)
| Benchmark | Mistral Large | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Longer Query | 1261 | 1476 |
Writing & Preference Qwen3.5 Max Preview leads
Mistral Large: 40.7 (#242), Qwen3.5 Max Preview: 66.0 (#41)
| Benchmark | Mistral Large | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Text | 1266 | 1470 |
| LMArena Creative Writing | 1243 | 1464 |
| LMArena Multi-Turn | 1260 | 1478 |
| Short-Story Creative Writing | 69% | — |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |
| LiveBench Language | 39.4% | — |
Frequently asked questions
Is Mistral Large better than Qwen3.5 Max Preview?
Qwen3.5 Max Preview is the stronger model overall, scoring 45.3 to 31.9 on the Noometry Index.
Is Mistral Large or Qwen3.5 Max Preview better for coding?
Qwen3.5 Max Preview scores higher on coding benchmarks: 44.0 versus 34.3 in the Noometry coding category.
How many benchmarks do Mistral Large and Qwen3.5 Max Preview share?
17 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Qwen3.5 Max Preview has 17.