Model comparison
Mistral Large vs Qwen3.5 35B-A3B
Qwen3.5 35B-A3B is the stronger model overall, scoring 41.7 to 31.6 on the Noometry Index.
Last verified . 25 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. Mistral Large 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 math, where Qwen3.5 35B-A3B leads 38.4 to 17.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Mistral Large and 70% for Qwen3.5 35B-A3B.
- Qwen3.5 35B-A3B is cheaper at $0.25 / $2 per million input/output tokens, against $2 / $6 for Mistral Large.
- Qwen3.5 35B-A3B accepts more context: 262K tokens versus 131K.
Side by side
| Mistral Large | Qwen3.5 35B-A3B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.6 | 41.7 |
| Released | 2024-02-26 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 16K | 66K |
| Input $ / M tokens | $2 | $0.25 |
| Output $ / M tokens | $6 | $2 |
| Results tracked | 51 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mistral Large: 33.8 (#240), Qwen3.5 35B-A3B: 33.5 (#244)
| Benchmark | Mistral Large | Qwen3.5 35B-A3B |
|---|---|---|
| SciCode | 36.2% | 29.3% |
| LMArena Coding | 1277 | 1410 |
| LMArena WebDev | — | 1254 |
| BigCodeBench Instruct | 30% | — |
| LiveBench Coding | 47.1% | — |
| BigCodeBench Complete | 38.3% | — |
| ALE-Bench | 264.7 | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |
Agentic & Tool Use Not comparable
Mistral Large: 28.4 (#83), Qwen3.5 35B-A3B: —
| Benchmark | Mistral Large | Qwen3.5 35B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |
Reasoning Qwen3.5 35B-A3B leads
Mistral Large: 15.4 (#305), Qwen3.5 35B-A3B: 23.9 (#158)
| Benchmark | Mistral Large | Qwen3.5 35B-A3B |
|---|---|---|
| CritPt | 0% | 0.6% |
| LMArena Hard Prompts | 1257 | 1400 |
| DTBench | 65.1% | 80% |
| LMCA | 16.7% | 29.5% |
| Epoch Capabilities Index | 128.52 | 142.52 |
| SimpleBench | 22.5% | — |
| Chess Puzzles | — | 10% |
| LiveBench Reasoning | 43.5% | — |
| LiveBench Data Analysis | 50.1% | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |
Math Qwen3.5 35B-A3B leads
Mistral Large: 17.1 (#285), Qwen3.5 35B-A3B: 38.4 (#86)
| Benchmark | Mistral Large | Qwen3.5 35B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 70% |
| LMArena Math | 1262 | 1404 |
| MathArena Final-Answer Competitions | — | 56% |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Qwen3.5 35B-A3B leads
Mistral Large: 30.0 (#224), Qwen3.5 35B-A3B: 47.7 (#73)
| Benchmark | Mistral Large | Qwen3.5 35B-A3B |
|---|---|---|
| GPQA Diamond | 51.3% | 83.5% |
| Vectara Hallucination Rate | 4.5% | 10.5% |
| LMArena Expert | 1232 | 1408 |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |
Multilingual Qwen3.5 35B-A3B leads
Mistral Large: 40.1 (#214), Qwen3.5 35B-A3B: 50.2 (#122)
| Benchmark | Mistral Large | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | 1237 | 1379 |
| LMArena Chinese | 1240 | 1458 |
| LMArena French | 1324 | 1412 |
| LMArena German | 1254 | 1367 |
| LMArena Japanese | 1187 | 1326 |
| LMArena Korean | 1202 | 1354 |
| LMArena Russian | 1257 | 1377 |
| LMArena Spanish | 1268 | 1390 |
Instruction Following Qwen3.5 35B-A3B leads
Mistral Large: 68.1 (#186), Qwen3.5 35B-A3B: 73.0 (#123)
| Benchmark | Mistral Large | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | 1249 | 1379 |
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
Long Context Qwen3.5 35B-A3B leads
Mistral Large: 38.3 (#194), Qwen3.5 35B-A3B: 42.4 (#122)
| Benchmark | Mistral Large | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | 1262 | 1390 |
Writing & Preference Qwen3.5 35B-A3B leads
Mistral Large: 40.9 (#237), Qwen3.5 35B-A3B: 58.1 (#118)
| Benchmark | Mistral Large | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | 1266 | 1395 |
| LMArena Creative Writing | 1243 | 1347 |
| LMArena Multi-Turn | 1260 | 1391 |
| Short-Story Creative Writing | 69% | — |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |
| LiveBench Language | 39.4% | — |
Frequently asked questions
Is Mistral Large better than Qwen3.5 35B-A3B?
Qwen3.5 35B-A3B is the stronger model overall, scoring 41.7 to 31.6 on the Noometry Index.
Which is cheaper, Mistral Large 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 Large lists at $2 and $6.
Is Mistral Large 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?
Qwen3.5 35B-A3B does, with 262K tokens against 131K.
How many benchmarks do Mistral Large and Qwen3.5 35B-A3B share?
25 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Qwen3.5 35B-A3B has 28.