Model comparison
Mistral Large vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 45.7 to 31.6 on the Noometry Index.
Last verified . 23 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Mistral Large scores higher in 0 categories and Qwen3.5 397B-A17B in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.5 397B-A17B leads 44.9 to 17.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Mistral Large and 88.9% for Qwen3.5 397B-A17B.
- Qwen3.5 397B-A17B is cheaper at $0.60 / $3.60 per million input/output tokens, against $2 / $6 for Mistral Large.
- Qwen3.5 397B-A17B accepts more context: 262K tokens versus 131K.
Side by side
| Mistral Large | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.6 | 45.7 |
| Released | 2024-02-26 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 16K | 66K |
| Input $ / M tokens | $2 | $0.60 |
| Output $ / M tokens | $6 | $3.60 |
| Results tracked | 51 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 397B-A17B leads
Mistral Large: 33.8 (#240), Qwen3.5 397B-A17B: 41.7 (#108)
| Benchmark | Mistral Large | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Coding | 1277 | 1464 |
| LMArena WebDev | — | 1400 |
| SciCode | 36.2% | — |
| BigCodeBench Instruct | 30% | — |
| LiveBench Coding | 47.1% | — |
| BigCodeBench Complete | 38.3% | — |
| ALE-Bench | 264.7 | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |
Agentic & Tool Use Qwen3.5 397B-A17B leads
Mistral Large: 28.4 (#83), Qwen3.5 397B-A17B: 33.2 (#51)
| Benchmark | Mistral Large | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| Berkeley Function Calling Leaderboard | 38.4% | — |
| 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 Large: 15.4 (#305), Qwen3.5 397B-A17B: 33.6 (#62)
| Benchmark | Mistral Large | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1448 |
| DTBench | 65.1% | 87.5% |
| LMCA | 16.7% | 37.9% |
| Epoch Capabilities Index | 128.52 | 146.64 |
| SimpleBench | 22.5% | — |
| Kagi LLM Benchmark | — | 73.7% |
| NYT Connections (extended) | — | 58.9% |
| CritPt | 0% | — |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 65.1% |
| LiveBench Reasoning | 43.5% | — |
| Mystery Game Puzzles | — | 18% |
| LiveBench Data Analysis | 50.1% | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |
Math Qwen3.5 397B-A17B leads
Mistral Large: 17.1 (#285), Qwen3.5 397B-A17B: 44.9 (#64)
| Benchmark | Mistral Large | Qwen3.5 397B-A17B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 88.9% |
| LMArena Math | 1262 | 1455 |
| FrontierMath (Tiers 1-3) | — | 31.2% |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Qwen3.5 397B-A17B leads
Mistral Large: 30.0 (#224), Qwen3.5 397B-A17B: 53.3 (#53)
| Benchmark | Mistral Large | Qwen3.5 397B-A17B |
|---|---|---|
| GPQA Diamond | 51.3% | 86.4% |
| LMArena Expert | 1232 | 1461 |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |
Multimodal Not comparable
Mistral Large: —, Qwen3.5 397B-A17B: 40.0 (#42)
| Benchmark | Mistral Large | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1262 |
Multilingual Qwen3.5 397B-A17B leads
Mistral Large: 40.1 (#214), Qwen3.5 397B-A17B: 54.0 (#56)
| Benchmark | Mistral Large | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1237 | 1431 |
| LMArena Chinese | 1240 | 1501 |
| LMArena French | 1324 | 1461 |
| LMArena German | 1254 | 1447 |
| LMArena Japanese | 1187 | 1427 |
| LMArena Korean | 1202 | 1382 |
| LMArena Russian | 1257 | 1429 |
| LMArena Spanish | 1268 | 1443 |
Instruction Following Qwen3.5 397B-A17B leads
Mistral Large: 68.1 (#186), Qwen3.5 397B-A17B: 75.2 (#73)
| Benchmark | Mistral Large | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1249 | 1424 |
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
Long Context Qwen3.5 397B-A17B leads
Mistral Large: 38.3 (#194), Qwen3.5 397B-A17B: 44.1 (#71)
| Benchmark | Mistral Large | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1262 | 1442 |
Writing & Preference Qwen3.5 397B-A17B leads
Mistral Large: 40.9 (#237), Qwen3.5 397B-A17B: 62.5 (#74)
| Benchmark | Mistral Large | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1266 | 1438 |
| LMArena Creative Writing | 1243 | 1401 |
| EQ-Bench Creative Writing | 985 | 1478 |
| LMArena Multi-Turn | 1260 | 1447 |
| Short-Story Creative Writing | 69% | — |
| WildBench | 80.1% | — |
| LiveBench Language | 39.4% | — |
Frequently asked questions
Is Mistral Large better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 45.7 to 31.6 on the Noometry Index.
Which is cheaper, Mistral Large 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 Large lists at $2 and $6.
Is Mistral Large or Qwen3.5 397B-A17B better for coding?
Qwen3.5 397B-A17B scores higher on coding benchmarks: 41.7 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5 397B-A17B does, with 262K tokens against 131K.
How many benchmarks do Mistral Large and Qwen3.5 397B-A17B share?
23 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Qwen3.5 397B-A17B has 36.