Model comparison
Mistral Medium 3.5 vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 40.2 on the Noometry Index.
Last verified . 21 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Mistral Medium 3.5 scores higher in 0 categories and Qwen3.5 397B-A17B in 9 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 397B-A17B leads 34.5 to 17.3.
- The biggest single-benchmark swing is NYT Connections (extended): 12.9% for Mistral Medium 3.5 and 58.9% for Qwen3.5 397B-A17B.
- Qwen3.5 397B-A17B is cheaper at $0.60 / $3.60 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
Side by side
| Mistral Medium 3.5 | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 40.2 | 46.0 |
| Released | — | 2026-02-01 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 210K | 66K |
| Input $ / M tokens | $1.50 | $0.60 |
| Output $ / M tokens | $7.50 | $3.60 |
| Results tracked | 22 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 397B-A17B leads
Mistral Medium 3.5: 36.0 (#213), Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | Mistral Medium 3.5 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena WebDev | 1264 | 1400 |
| LMArena Coding | 1461 | 1465 |
Agentic & Tool Use Not comparable
Mistral Medium 3.5: —, Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | Mistral Medium 3.5 | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
Reasoning Qwen3.5 397B-A17B leads
Mistral Medium 3.5: 17.3 (#295), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | Mistral Medium 3.5 | Qwen3.5 397B-A17B |
|---|---|---|
| Kagi LLM Benchmark | 41.4% | 73.7% |
| NYT Connections (extended) | 12.9% | 58.9% |
| LMArena Hard Prompts | 1436 | 1448 |
| Epoch Capabilities Index | 141.35 | 146.65 |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 65.1% |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 87.5% |
| LMCA | — | 37.9% |
Math Qwen3.5 397B-A17B leads
Mistral Medium 3.5: 39.1 (#113), Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | Mistral Medium 3.5 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Math | 1431 | 1454 |
| FrontierMath (Tiers 1-3) | — | 31.2% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
Knowledge Qwen3.5 397B-A17B leads
Mistral Medium 3.5: 40.0 (#126), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | Mistral Medium 3.5 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Expert | 1432 | 1462 |
| GPQA Diamond | — | 86.4% |
Multimodal Qwen3.5 397B-A17B leads
Mistral Medium 3.5: 38.3 (#65), Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | Mistral Medium 3.5 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | 1223 | 1263 |
Multilingual Qwen3.5 397B-A17B leads
Mistral Medium 3.5: 51.9 (#100), Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | Mistral Medium 3.5 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1404 | 1430 |
| LMArena Chinese | 1442 | 1500 |
| LMArena French | 1448 | 1461 |
| LMArena German | 1451 | 1447 |
| LMArena Korean | 1385 | 1384 |
| LMArena Russian | 1395 | 1429 |
| LMArena Spanish | 1409 | 1441 |
| LMArena Japanese | — | 1426 |
Instruction Following Too close to call
Mistral Medium 3.5: 74.6 (#90), Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | Mistral Medium 3.5 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1415 | 1424 |
Long Context Too close to call
Mistral Medium 3.5: 43.2 (#103), Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | Mistral Medium 3.5 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1415 | 1442 |
Writing & Preference Qwen3.5 397B-A17B leads
Mistral Medium 3.5: 58.5 (#117), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | Mistral Medium 3.5 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1421 | 1438 |
| LMArena Creative Writing | 1374 | 1401 |
| LMArena Multi-Turn | 1423 | 1446 |
| EQ-Bench Creative Writing | — | 1478 |
| EQ-Bench 4 | 993 | — |
Frequently asked questions
Is Mistral Medium 3.5 better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 40.2 on the Noometry Index.
Which is cheaper, Mistral Medium 3.5 or Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is cheaper. It lists at $0.60 per million input tokens and $3.60 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.
Is Mistral Medium 3.5 or Qwen3.5 397B-A17B better for coding?
Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 36.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Mistral Medium 3.5 and Qwen3.5 397B-A17B share?
21 benchmarks have published results for both models. Mistral Medium 3.5 has 22 scored results on Noometry and Qwen3.5 397B-A17B has 36.