Model comparison
Mistral Medium 3.1 vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 31.9 on the Noometry Index. Mistral Medium 3.1 costs 3.8× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. Mistral Medium 3.1 scores higher in 0 categories and Qwen3.8 Max in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.8 Max leads 54.4 to 10.6.
- The biggest single-benchmark swing is NYT Connections (extended): 6.5% for Mistral Medium 3.1 and 88.3% for Qwen3.8 Max.
- Mistral Medium 3.1 is cheaper at $0.40 / $2 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Qwen3.8 Max accepts more context: 1M tokens versus 131K.
Side by side
| Mistral Medium 3.1 | Qwen3.8 Max | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.9 | 56.8 |
| Released | — | 2026-08-02 |
| Weights | Proprietary | Proprietary |
| Context window | 131K | 1M |
| Max output | 105K | 131K |
| Input $ / M tokens | $0.40 | $2 |
| Output $ / M tokens | $2 | $6 |
| Results tracked | 3 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mistral Medium 3.1: —, Qwen3.8 Max: 53.5 (#29)
| Benchmark | Mistral Medium 3.1 | Qwen3.8 Max |
|---|---|---|
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
| LMArena Coding | — | 1502 |
Agentic & Tool Use Not comparable
Mistral Medium 3.1: —, Qwen3.8 Max: 45.4 (#14)
| Benchmark | Mistral Medium 3.1 | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
Mistral Medium 3.1: 10.6 (#341), Qwen3.8 Max: 54.4 (#26)
| Benchmark | Mistral Medium 3.1 | Qwen3.8 Max |
|---|---|---|
| NYT Connections (extended) | 6.5% | 88.3% |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| Thematic Generalization | 20.3% | — |
| LMArena Hard Prompts | — | 1496 |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LMCA | — | 46.2% |
| Epoch Capabilities Index | — | 156.41 |
Math Not comparable
Mistral Medium 3.1: —, Qwen3.8 Max: 73.2 (#20)
| Benchmark | Mistral Medium 3.1 | Qwen3.8 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 58% |
| LMArena Math | — | 1499 |
Knowledge Not comparable
Mistral Medium 3.1: —, Qwen3.8 Max: 61.7 (#27)
| Benchmark | Mistral Medium 3.1 | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 47.3% |
| LMArena Expert | — | 1507 |
Multimodal Not comparable
Mistral Medium 3.1: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | Mistral Medium 3.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Not comparable
Mistral Medium 3.1: —, Qwen3.8 Max: 56.7 (#18)
| Benchmark | Mistral Medium 3.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | — | 1472 |
| LMArena Chinese | — | 1538 |
| LMArena French | — | 1503 |
| LMArena German | — | 1483 |
| LMArena Japanese | — | 1467 |
| LMArena Korean | — | 1461 |
| LMArena Russian | — | 1481 |
| LMArena Spanish | — | 1492 |
Instruction Following Not comparable
Mistral Medium 3.1: —, Qwen3.8 Max: 77.6 (#17)
| Benchmark | Mistral Medium 3.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | — | 1479 |
Long Context Not comparable
Mistral Medium 3.1: —, Qwen3.8 Max: 45.6 (#31)
| Benchmark | Mistral Medium 3.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | — | 1489 |
Writing & Preference Qwen3.8 Max leads
Mistral Medium 3.1: 55.5 (#145), Qwen3.8 Max: 67.1 (#30)
| Benchmark | Mistral Medium 3.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Text | — | 1483 |
| LMArena Creative Writing | — | 1479 |
| EQ-Bench Creative Writing | 1476 | — |
| LMArena Multi-Turn | — | 1489 |
Frequently asked questions
Is Mistral Medium 3.1 better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 31.9 on the Noometry Index. Mistral Medium 3.1 costs 3.8× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Which is cheaper, Mistral Medium 3.1 or Qwen3.8 Max?
Mistral Medium 3.1 is cheaper. It lists at $0.40 per million input tokens and $2 per million output tokens; Qwen3.8 Max lists at $2 and $6.
Which has the bigger context window?
Qwen3.8 Max does, with 1M tokens against 131K.
How many benchmarks do Mistral Medium 3.1 and Qwen3.8 Max share?
1 benchmark has published results for both models. Mistral Medium 3.1 has 3 scored results on Noometry and Qwen3.8 Max has 39.