Model comparison
Mistral vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 29.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Mistral scores higher in 0 categories and Qwen3.8 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 22.3.
Side by side
| Mistral | Qwen3.8 Max | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 29.9 | 56.8 |
| Released | — | 2026-08-02 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 131K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 22 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Mistral: 33.8 (#250), Qwen3.8 Max: 53.5 (#29)
| Benchmark | Mistral | Qwen3.8 Max |
|---|---|---|
| LMArena Coding | 1162 | 1502 |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
Agentic & Tool Use Not comparable
Mistral: —, Qwen3.8 Max: 45.4 (#14)
| Benchmark | Mistral | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
Mistral: 22.2 (#200), Qwen3.8 Max: 54.4 (#26)
| Benchmark | Mistral | Qwen3.8 Max |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1496 |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LMCA | — | 46.2% |
| Epoch Capabilities Index | — | 156.41 |
Math Qwen3.8 Max leads
Mistral: 22.3 (#278), Qwen3.8 Max: 73.2 (#20)
| Benchmark | Mistral | Qwen3.8 Max |
|---|---|---|
| LMArena Math | 1180 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 58% |
| Omni-MATH | 7.2% | — |
Knowledge Qwen3.8 Max leads
Mistral: 16.6 (#288), Qwen3.8 Max: 61.7 (#27)
| Benchmark | Mistral | Qwen3.8 Max |
|---|---|---|
| LMArena Expert | 1125 | 1507 |
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 47.3% |
| MMLU-Pro | 27.7% | — |
| GPQA (HELM) | 30.3% | — |
Multimodal Not comparable
Mistral: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | Mistral | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Qwen3.8 Max leads
Mistral: 32.8 (#254), Qwen3.8 Max: 56.7 (#18)
| Benchmark | Mistral | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1129 | 1472 |
| LMArena Chinese | 1109 | 1538 |
| LMArena French | 1180 | 1503 |
| LMArena German | 1155 | 1483 |
| LMArena Japanese | 1013 | 1467 |
| LMArena Korean | 1032 | 1461 |
| LMArena Russian | 1168 | 1481 |
| LMArena Spanish | 1143 | 1492 |
Instruction Following Qwen3.8 Max leads
Mistral: 52.6 (#288), Qwen3.8 Max: 77.6 (#17)
| Benchmark | Mistral | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1152 | 1479 |
| IFEval | 56.8% | — |
Long Context Qwen3.8 Max leads
Mistral: 35.0 (#245), Qwen3.8 Max: 45.6 (#31)
| Benchmark | Mistral | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1153 | 1489 |
Writing & Preference Qwen3.8 Max leads
Mistral: 37.0 (#260), Qwen3.8 Max: 67.1 (#30)
| Benchmark | Mistral | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1165 | 1483 |
| LMArena Creative Writing | 1158 | 1479 |
| LMArena Multi-Turn | 1147 | 1489 |
| WildBench | 66% | — |
Frequently asked questions
Is Mistral better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 29.9 on the Noometry Index.
Is Mistral or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 33.8 in the Noometry coding category.
How many benchmarks do Mistral and Qwen3.8 Max share?
17 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Qwen3.8 Max has 39.