Model comparison
Mistral Large 3 vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 39.1 on the Noometry Index. Mistral Large 3 costs 7.8× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. Mistral Large 3 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 reasoning, where Qwen3.6 Max Preview leads 41.7 to 15.2.
- The biggest single-benchmark swing is NYT Connections (extended): 7.5% for Mistral Large 3 and 74.1% for Qwen3.6 Max Preview.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- Mistral Large 3 has downloadable open weights; the other is API-only.
Side by side
| Mistral Large 3 | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 39.1 | 51.5 |
| Released | 2025-12-02 | 2026-04-20 |
| Weights | Open | Proprietary |
| Context window | 262K | 262K |
| Max output | 8K | 66K |
| Input $ / M tokens | $0.25 | $1.30 |
| Output $ / M tokens | $0.75 | $7.80 |
| Results tracked | 24 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
Mistral Large 3: 34.4 (#237), Qwen3.6 Max Preview: 48.7 (#54)
| Benchmark | Mistral Large 3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena WebDev | 1230 | 1482 |
| LMArena Coding | 1448 | 1471 |
| SWE-bench Verified | — | 76.7% |
Agentic & Tool Use Not comparable
Mistral Large 3: —, Qwen3.6 Max Preview: —
| Benchmark | Mistral Large 3 | Qwen3.6 Max Preview |
|---|---|---|
| Vending-Bench 2 | — | 4,254 |
Reasoning Qwen3.6 Max Preview leads
Mistral Large 3: 15.2 (#319), Qwen3.6 Max Preview: 41.7 (#53)
| Benchmark | Mistral Large 3 | Qwen3.6 Max Preview |
|---|---|---|
| NYT Connections (extended) | 7.5% | 74.1% |
| LMArena Hard Prompts | 1429 | 1457 |
| SimpleBench | — | 63% |
| Kagi LLM Benchmark | 50.9% | — |
| Chess Puzzles | — | 20% |
| Thematic Generalization | 23% | — |
| Mystery Game Puzzles | — | 19% |
| DTBench | — | 87.2% |
| LMCA | — | 42.5% |
| Epoch Capabilities Index | — | 149.24 |
Math Qwen3.6 Max Preview leads
Mistral Large 3: 38.7 (#129), Qwen3.6 Max Preview: 54.1 (#46)
| Benchmark | Mistral Large 3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Math | 1414 | 1465 |
| OTIS Mock AIME 2024-2025 | — | 91.1% |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Qwen3.6 Max Preview leads
Mistral Large 3: 36.0 (#177), Qwen3.6 Max Preview: 57.6 (#39)
| Benchmark | Mistral Large 3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Expert | 1421 | 1478 |
| GPQA Diamond | — | 87.4% |
| SimpleQA Verified | — | 52% |
| Vectara Hallucination Rate | 14.5% | — |
Multimodal Not comparable
Mistral Large 3: 38.2 (#66), Qwen3.6 Max Preview: —
| Benchmark | Mistral Large 3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Vision | 1221 | — |
Multilingual Qwen3.6 Max Preview leads
Mistral Large 3: 52.5 (#84), Qwen3.6 Max Preview: 54.2 (#48)
| Benchmark | Mistral Large 3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1413 | 1437 |
| LMArena Chinese | 1447 | 1487 |
| LMArena French | 1455 | 1449 |
| LMArena Russian | 1411 | 1445 |
| LMArena Spanish | 1440 | 1454 |
| LMArena German | 1437 | — |
| LMArena Japanese | 1394 | — |
| LMArena Korean | 1384 | — |
Instruction Following Qwen3.6 Max Preview leads
Mistral Large 3: 74.0 (#108), Qwen3.6 Max Preview: 75.7 (#55)
| Benchmark | Mistral Large 3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1403 | 1438 |
Long Context Qwen3.6 Max Preview leads
Mistral Large 3: 43.1 (#105), Qwen3.6 Max Preview: 44.6 (#61)
| Benchmark | Mistral Large 3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1413 | 1457 |
Writing & Preference Qwen3.6 Max Preview leads
Mistral Large 3: 60.0 (#101), Qwen3.6 Max Preview: 63.8 (#60)
| Benchmark | Mistral Large 3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1428 | 1447 |
| LMArena Creative Writing | 1386 | 1435 |
| LMArena Multi-Turn | 1429 | 1456 |
| EQ-Bench Creative Writing | 1412 | — |
Frequently asked questions
Is Mistral Large 3 better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 39.1 on the Noometry Index. Mistral Large 3 costs 7.8× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Which is cheaper, Mistral Large 3 or Qwen3.6 Max Preview?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.
Is Mistral Large 3 or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.7 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Mistral Large 3 and Qwen3.6 Max Preview share?
16 benchmarks have published results for both models. Mistral Large 3 has 24 scored results on Noometry and Qwen3.6 Max Preview has 29.