Model comparison
Devstral Medium vs Qwen3.8 Max
Qwen3.8 Max has enough public results to be ranked (#22); Devstral Medium does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. Devstral Medium 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 21.1.
- Devstral Medium 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 262K.
- Devstral Medium has downloadable open weights; the other is API-only.
Side by side
| Devstral Medium | Qwen3.8 Max | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.1 | 56.8 |
| Released | 2025-07-10 | 2026-08-02 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 262K | 131K |
| Input $ / M tokens | $0.40 | $2 |
| Output $ / M tokens | $2 | $6 |
| Results tracked | 2 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Devstral Medium: 24.3, Qwen3.8 Max: 53.5 (#29)
| Benchmark | Devstral Medium | Qwen3.8 Max |
|---|---|---|
| LMArena WebDev | 1076 | 1674 |
| DeepSWE | — | 57.5% |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
| LMArena Coding | — | 1502 |
Agentic & Tool Use Not comparable
Devstral Medium: —, Qwen3.8 Max: 45.4 (#14)
| Benchmark | Devstral Medium | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
Devstral Medium: 21.1, Qwen3.8 Max: 54.4 (#26)
| Benchmark | Devstral Medium | Qwen3.8 Max |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| LMArena Hard Prompts | — | 1496 |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LMCA | — | 46.2% |
| Epoch Capabilities Index | — | 156.41 |
Math Not comparable
Devstral Medium: —, Qwen3.8 Max: 73.2 (#20)
| Benchmark | Devstral Medium | 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
Devstral Medium: —, Qwen3.8 Max: 61.7 (#27)
| Benchmark | Devstral Medium | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 47.3% |
| LMArena Expert | — | 1507 |
Multimodal Not comparable
Devstral Medium: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | Devstral Medium | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Not comparable
Devstral Medium: —, Qwen3.8 Max: 56.7 (#18)
| Benchmark | Devstral Medium | 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
Devstral Medium: —, Qwen3.8 Max: 77.6 (#17)
| Benchmark | Devstral Medium | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | — | 1479 |
Long Context Not comparable
Devstral Medium: —, Qwen3.8 Max: 45.6 (#31)
| Benchmark | Devstral Medium | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | — | 1489 |
Writing & Preference Not comparable
Devstral Medium: —, Qwen3.8 Max: 67.1 (#30)
| Benchmark | Devstral Medium | Qwen3.8 Max |
|---|---|---|
| LMArena Text | — | 1483 |
| LMArena Creative Writing | — | 1479 |
| LMArena Multi-Turn | — | 1489 |
Frequently asked questions
Is Devstral Medium better than Qwen3.8 Max?
Qwen3.8 Max has enough public results to be ranked (#22); Devstral Medium does not yet, so treat this comparison as directional.
Which is cheaper, Devstral Medium or Qwen3.8 Max?
Devstral Medium 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.
Is Devstral Medium or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 24.3 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 Max does, with 1M tokens against 262K.
How many benchmarks do Devstral Medium and Qwen3.8 Max share?
1 benchmark has published results for both models. Devstral Medium has 2 scored results on Noometry and Qwen3.8 Max has 39.