Model comparison
Mistral Large vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 31.6 on the Noometry Index.
Last verified . 21 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Mistral Large scores higher in 0 categories and Qwen3.6 Max Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 Max Preview leads 52.2 to 17.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Mistral Large and 91.1% for Qwen3.6 Max Preview.
- Both cost about the same: $2 input and $6 output per million tokens.
- Qwen3.6 Max Preview accepts more context: 262K tokens versus 131K.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Mistral Large | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.6 | 51.1 |
| Released | 2024-02-26 | 2026-04-20 |
| Weights | Open | Proprietary |
| Context window | 131K | 262K |
| Max output | 16K | 66K |
| Input $ / M tokens | $2 | $1.30 |
| Output $ / M tokens | $6 | $7.80 |
| Results tracked | 51 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
Mistral Large: 33.8 (#240), Qwen3.6 Max Preview: 48.6 (#50)
| Benchmark | Mistral Large | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Coding | 1277 | 1472 |
| SWE-bench Verified | — | 76.7% |
| LMArena WebDev | — | 1482 |
| 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 Not comparable
Mistral Large: 28.4 (#83), Qwen3.6 Max Preview: —
| Benchmark | Mistral Large | Qwen3.6 Max Preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |
| Vending-Bench 2 | — | 4,254 |
Reasoning Qwen3.6 Max Preview leads
Mistral Large: 15.4 (#305), Qwen3.6 Max Preview: 40.8 (#47)
| Benchmark | Mistral Large | Qwen3.6 Max Preview |
|---|---|---|
| SimpleBench | 22.5% | 63% |
| LMArena Hard Prompts | 1257 | 1457 |
| DTBench | 65.1% | 87.2% |
| LMCA | 16.7% | 42.5% |
| Epoch Capabilities Index | 128.52 | 149.27 |
| NYT Connections (extended) | — | 74.1% |
| CritPt | 0% | — |
| Chess Puzzles | — | 20% |
| LiveBench Reasoning | 43.5% | — |
| Mystery Game Puzzles | — | 19% |
| LiveBench Data Analysis | 50.1% | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |
Math Qwen3.6 Max Preview leads
Mistral Large: 17.1 (#285), Qwen3.6 Max Preview: 52.2 (#40)
| Benchmark | Mistral Large | Qwen3.6 Max Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 91.1% |
| LMArena Math | 1262 | 1465 |
| FrontierMath (Feb 2025 set) | 0.3% | 23.1% |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Qwen3.6 Max Preview leads
Mistral Large: 30.0 (#224), Qwen3.6 Max Preview: 57.6 (#35)
| Benchmark | Mistral Large | Qwen3.6 Max Preview |
|---|---|---|
| GPQA Diamond | 51.3% | 87.4% |
| LMArena Expert | 1232 | 1476 |
| SimpleQA Verified | — | 52% |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |
Multilingual Qwen3.6 Max Preview leads
Mistral Large: 40.1 (#214), Qwen3.6 Max Preview: 54.3 (#46)
| Benchmark | Mistral Large | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1237 | 1436 |
| LMArena Chinese | 1240 | 1487 |
| LMArena French | 1324 | 1449 |
| LMArena Russian | 1257 | 1444 |
| LMArena Spanish | 1268 | 1452 |
| LMArena German | 1254 | — |
| LMArena Japanese | 1187 | — |
| LMArena Korean | 1202 | — |
Instruction Following Qwen3.6 Max Preview leads
Mistral Large: 68.1 (#186), Qwen3.6 Max Preview: 75.8 (#51)
| Benchmark | Mistral Large | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1249 | 1437 |
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
Long Context Qwen3.6 Max Preview leads
Mistral Large: 38.3 (#194), Qwen3.6 Max Preview: 44.6 (#59)
| Benchmark | Mistral Large | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1262 | 1457 |
Writing & Preference Qwen3.6 Max Preview leads
Mistral Large: 40.9 (#237), Qwen3.6 Max Preview: 64.0 (#58)
| Benchmark | Mistral Large | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1266 | 1447 |
| LMArena Creative Writing | 1243 | 1435 |
| LMArena Multi-Turn | 1260 | 1456 |
| 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 Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 31.6 on the Noometry Index.
Which is cheaper, Mistral Large or Qwen3.6 Max Preview?
Qwen3.6 Max Preview is cheaper. It lists at $1.30 per million input tokens and $7.80 per million output tokens; Mistral Large lists at $2 and $6.
Is Mistral Large or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.6 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Max Preview does, with 262K tokens against 131K.
How many benchmarks do Mistral Large and Qwen3.6 Max Preview share?
21 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Qwen3.6 Max Preview has 29.