Model comparison
Mistral Medium vs Qwen3.5 35B-A3B
Qwen3.5 35B-A3B is the stronger model overall, scoring 41.7 to 36.0 on the Noometry Index.
Last verified . 24 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 24 benchmarks with published results for both. Mistral Medium scores higher in 5 categories and Qwen3.5 35B-A3B in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5 35B-A3B leads 47.7 to 24.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 32.2% for Mistral Medium and 70% for Qwen3.5 35B-A3B.
- Qwen3.5 35B-A3B is cheaper at $0.25 / $2 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
Side by side
| Mistral Medium | Qwen3.5 35B-A3B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 36.0 | 41.7 |
| Released | 2023-12-11 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 262K | 66K |
| Input $ / M tokens | $1.50 | $0.25 |
| Output $ / M tokens | $7.50 | $2 |
| Results tracked | 36 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mistral Medium: 33.8 (#241), Qwen3.5 35B-A3B: 33.5 (#244)
| Benchmark | Mistral Medium | Qwen3.5 35B-A3B |
|---|---|---|
| SciCode | 40.2% | 29.3% |
| LMArena Coding | 1434 | 1410 |
| FrontierCode | 8% | — |
| LMArena WebDev | — | 1254 |
| WeirdML | 43.7% | — |
| ALE-Bench | 763.98 | — |
Agentic & Tool Use Not comparable
Mistral Medium: 28.1 (#84), Qwen3.5 35B-A3B: —
| Benchmark | Mistral Medium | Qwen3.5 35B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |
Reasoning Too close to call
Mistral Medium: 23.3 (#165), Qwen3.5 35B-A3B: 23.9 (#158)
| Benchmark | Mistral Medium | Qwen3.5 35B-A3B |
|---|---|---|
| CritPt | 0% | 0.6% |
| LMArena Hard Prompts | 1426 | 1400 |
| DTBench | 75.5% | 80% |
| LMCA | 26.1% | 29.5% |
| Kagi LLM Benchmark | 50% | — |
| Chess Puzzles | — | 10% |
| Surface Evolver Bench | 26.9% | — |
| Epoch Capabilities Index | — | 142.52 |
Math Qwen3.5 35B-A3B leads
Mistral Medium: 27.2 (#238), Qwen3.5 35B-A3B: 38.4 (#86)
| Benchmark | Mistral Medium | Qwen3.5 35B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 32.2% | 70% |
| LMArena Math | 1409 | 1404 |
| MathArena Final-Answer Competitions | — | 56% |
| ProofBench | 9% | — |
| MATH Level 5 | 81.6% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Qwen3.5 35B-A3B leads
Mistral Medium: 24.9 (#260), Qwen3.5 35B-A3B: 47.7 (#73)
| Benchmark | Mistral Medium | Qwen3.5 35B-A3B |
|---|---|---|
| GPQA Diamond | 59.5% | 83.5% |
| Vectara Hallucination Rate | 22.7% | 10.5% |
| LMArena Expert | 1408 | 1408 |
| Humanity's Last Exam | 4.5% | — |
Multimodal Not comparable
Mistral Medium: 34.6 (#82), Qwen3.5 35B-A3B: —
| Benchmark | Mistral Medium | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Vision | 1172 | — |
Multilingual Mistral Medium leads
Mistral Medium: 52.3 (#86), Qwen3.5 35B-A3B: 50.2 (#122)
| Benchmark | Mistral Medium | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | 1408 | 1379 |
| LMArena Chinese | 1448 | 1458 |
| LMArena French | 1460 | 1412 |
| LMArena German | 1433 | 1367 |
| LMArena Japanese | 1378 | 1326 |
| LMArena Korean | 1382 | 1354 |
| LMArena Russian | 1411 | 1377 |
| LMArena Spanish | 1433 | 1390 |
Instruction Following Too close to call
Mistral Medium: 73.9 (#111), Qwen3.5 35B-A3B: 73.0 (#123)
| Benchmark | Mistral Medium | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | 1398 | 1379 |
Long Context Too close to call
Mistral Medium: 42.9 (#108), Qwen3.5 35B-A3B: 42.4 (#122)
| Benchmark | Mistral Medium | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | 1406 | 1390 |
Writing & Preference Mistral Medium leads
Mistral Medium: 60.2 (#97), Qwen3.5 35B-A3B: 58.1 (#118)
| Benchmark | Mistral Medium | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | 1424 | 1395 |
| LMArena Creative Writing | 1391 | 1347 |
| LMArena Multi-Turn | 1418 | 1391 |
| Short-Story Creative Writing | 77.3% | — |
Frequently asked questions
Is Mistral Medium better than Qwen3.5 35B-A3B?
Qwen3.5 35B-A3B is the stronger model overall, scoring 41.7 to 36.0 on the Noometry Index.
Which is cheaper, Mistral Medium or Qwen3.5 35B-A3B?
Qwen3.5 35B-A3B is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Mistral Medium or Qwen3.5 35B-A3B better for coding?
They score almost the same on coding (33.8 vs 33.5); test both on your own repository before choosing.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Mistral Medium and Qwen3.5 35B-A3B share?
24 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Qwen3.5 35B-A3B has 28.