Model comparison
Mistral vs Qwen3.5 35B-A3B
Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 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 1 category and Qwen3.5 35B-A3B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5 35B-A3B leads 47.8 to 16.6.
- Qwen3.5 35B-A3B has downloadable open weights; the other is API-only.
Side by side
| Mistral | Qwen3.5 35B-A3B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 29.9 | 42.0 |
| Released | — | 2026-02-01 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $2 |
| Results tracked | 22 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mistral: 33.8 (#250), Qwen3.5 35B-A3B: 33.8 (#251)
| Benchmark | Mistral | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Coding | 1162 | 1410 |
| LMArena WebDev | — | 1254 |
| SciCode | — | 29.3% |
Reasoning Qwen3.5 35B-A3B leads
Mistral: 22.2 (#200), Qwen3.5 35B-A3B: 24.6 (#161)
| Benchmark | Mistral | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1400 |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 10% |
| DTBench | — | 80% |
| LMCA | — | 29.5% |
| Epoch Capabilities Index | — | 142.52 |
Math Qwen3.5 35B-A3B leads
Mistral: 22.3 (#278), Qwen3.5 35B-A3B: 39.9 (#97)
| Benchmark | Mistral | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Math | 1180 | 1404 |
| MathArena Final-Answer Competitions | — | 56% |
| OTIS Mock AIME 2024-2025 | — | 70% |
| Omni-MATH | 7.2% | — |
Knowledge Qwen3.5 35B-A3B leads
Mistral: 16.6 (#288), Qwen3.5 35B-A3B: 47.8 (#79)
| Benchmark | Mistral | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Expert | 1125 | 1408 |
| GPQA Diamond | — | 83.5% |
| MMLU-Pro | 27.7% | — |
| Vectara Hallucination Rate | — | 10.5% |
| GPQA (HELM) | 30.3% | — |
Multilingual Qwen3.5 35B-A3B leads
Mistral: 32.8 (#254), Qwen3.5 35B-A3B: 50.0 (#127)
| Benchmark | Mistral | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | 1129 | 1378 |
| LMArena Chinese | 1109 | 1457 |
| LMArena French | 1180 | 1412 |
| LMArena German | 1155 | 1367 |
| LMArena Japanese | 1013 | 1325 |
| LMArena Korean | 1032 | 1356 |
| LMArena Russian | 1168 | 1376 |
| LMArena Spanish | 1143 | 1392 |
Instruction Following Qwen3.5 35B-A3B leads
Mistral: 52.6 (#288), Qwen3.5 35B-A3B: 72.8 (#128)
| Benchmark | Mistral | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | 1152 | 1379 |
| IFEval | 56.8% | — |
Long Context Qwen3.5 35B-A3B leads
Mistral: 35.0 (#245), Qwen3.5 35B-A3B: 42.4 (#127)
| Benchmark | Mistral | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | 1153 | 1389 |
Writing & Preference Qwen3.5 35B-A3B leads
Mistral: 37.0 (#260), Qwen3.5 35B-A3B: 57.9 (#124)
| Benchmark | Mistral | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | 1165 | 1395 |
| LMArena Creative Writing | 1158 | 1346 |
| LMArena Multi-Turn | 1147 | 1390 |
| WildBench | 66% | — |
Frequently asked questions
Is Mistral better than Qwen3.5 35B-A3B?
Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 29.9 on the Noometry Index.
Is Mistral or Qwen3.5 35B-A3B better for coding?
They score almost the same on coding (33.8 vs 33.8); test both on your own repository before choosing.
How many benchmarks do Mistral and Qwen3.5 35B-A3B share?
17 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Qwen3.5 35B-A3B has 28.