Model comparison
Mistral Large 3 vs Qwen3 Max
Qwen3 Max is the stronger model overall, scoring 43.7 to 39.1 on the Noometry Index. Mistral Large 3 costs 6.4× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Mistral Large 3 scores higher in 2 categories and Qwen3 Max in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 Max leads 48.1 to 36.0.
- The biggest single-benchmark swing is NYT Connections (extended): 7.5% for Mistral Large 3 and 30.1% for Qwen3 Max.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
- Mistral Large 3 has downloadable open weights; the other is API-only.
Side by side
| Mistral Large 3 | Qwen3 Max | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 39.1 | 43.7 |
| Released | 2025-12-02 | 2025-09-23 |
| Weights | Open | Proprietary |
| Context window | 262K | 262K |
| Max output | 8K | 66K |
| Input $ / M tokens | $0.25 | $1.20 |
| Output $ / M tokens | $0.75 | $6 |
| Results tracked | 24 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 Max leads
Mistral Large 3: 34.4 (#237), Qwen3 Max: 43.0 (#93)
| Benchmark | Mistral Large 3 | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1448 | 1456 |
| LMArena WebDev | 1230 | — |
| ALE-Bench | — | 370.45 |
Agentic & Tool Use Not comparable
Mistral Large 3: —, Qwen3 Max: —
| Benchmark | Mistral Large 3 | Qwen3 Max |
|---|---|---|
| Vending-Bench 2 | — | 71.56 |
Reasoning Qwen3 Max leads
Mistral Large 3: 15.2 (#319), Qwen3 Max: 22.6 (#190)
| Benchmark | Mistral Large 3 | Qwen3 Max |
|---|---|---|
| Kagi LLM Benchmark | 50.9% | 72.5% |
| NYT Connections (extended) | 7.5% | 30.1% |
| LMArena Hard Prompts | 1429 | 1448 |
| Chess Puzzles | — | 4% |
| Thematic Generalization | 23% | — |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 82.1% |
| LMCA | — | 28.3% |
| Epoch Capabilities Index | — | 142.38 |
Math Too close to call
Mistral Large 3: 38.7 (#129), Qwen3 Max: 38.7 (#131)
| Benchmark | Mistral Large 3 | Qwen3 Max |
|---|---|---|
| LMArena Math | 1414 | 1446 |
| FrontierMath (Tiers 1-3) | — | 18.9% |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| MATH Level 5 | — | 97.1% |
Knowledge Qwen3 Max leads
Mistral Large 3: 36.0 (#177), Qwen3 Max: 48.1 (#78)
| Benchmark | Mistral Large 3 | Qwen3 Max |
|---|---|---|
| LMArena Expert | 1421 | 1455 |
| GPQA Diamond | — | 72.6% |
| SimpleQA Verified | — | 48.7% |
| Vectara Hallucination Rate | 14.5% | — |
Multimodal Not comparable
Mistral Large 3: 38.2 (#66), Qwen3 Max: —
| Benchmark | Mistral Large 3 | Qwen3 Max |
|---|---|---|
| LMArena Vision | 1221 | — |
Multilingual Qwen3 Max leads
Mistral Large 3: 52.5 (#84), Qwen3 Max: 53.7 (#62)
| Benchmark | Mistral Large 3 | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1413 | 1429 |
| LMArena Chinese | 1447 | 1478 |
| LMArena French | 1455 | 1449 |
| LMArena German | 1437 | 1463 |
| LMArena Japanese | 1394 | 1397 |
| LMArena Korean | 1384 | 1399 |
| LMArena Russian | 1411 | 1428 |
| LMArena Spanish | 1440 | 1462 |
Instruction Following Too close to call
Mistral Large 3: 74.0 (#108), Qwen3 Max: 74.8 (#87)
| Benchmark | Mistral Large 3 | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1403 | 1419 |
Long Context Mistral Large 3 leads
Mistral Large 3: 43.1 (#105), Qwen3 Max: 41.6 (#134)
| Benchmark | Mistral Large 3 | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1413 | 1438 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |
Writing & Preference Qwen3 Max leads
Mistral Large 3: 60.0 (#101), Qwen3 Max: 62.4 (#76)
| Benchmark | Mistral Large 3 | Qwen3 Max |
|---|---|---|
| LMArena Text | 1428 | 1439 |
| LMArena Creative Writing | 1386 | 1402 |
| LMArena Multi-Turn | 1429 | 1446 |
| EQ-Bench Creative Writing | 1412 | — |
Frequently asked questions
Is Mistral Large 3 better than Qwen3 Max?
Qwen3 Max is the stronger model overall, scoring 43.7 to 39.1 on the Noometry Index. Mistral Large 3 costs 6.4× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Which is cheaper, Mistral Large 3 or Qwen3 Max?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Qwen3 Max lists at $1.20 and $6.
Is Mistral Large 3 or Qwen3 Max better for coding?
Qwen3 Max scores higher on coding benchmarks: 43.0 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 Max share?
19 benchmarks have published results for both models. Mistral Large 3 has 24 scored results on Noometry and Qwen3 Max has 33.