Model comparison
Mistral Large 3 vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 38.6 on the Noometry Index. Mistral Large 3 costs 3.3× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Mistral Large 3 scores higher in 3 categories and Qwen3 235B-A22B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 235B-A22B leads 49.5 to 35.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 50.9% for Mistral Large 3 and 69.4% for Qwen3 235B-A22B.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.70 / $2.80 for Qwen3 235B-A22B.
- Mistral Large 3 accepts more context: 262K tokens versus 131K.
Side by side
| Mistral Large 3 | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 38.6 | 43.2 |
| Released | 2025-12-02 | 2025-04 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 8K | 16K |
| Input $ / M tokens | $0.25 | $0.70 |
| Output $ / M tokens | $0.75 | $2.80 |
| Results tracked | 24 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Mistral Large 3: 34.1 (#230), Qwen3 235B-A22B: 43.8 (#72)
| Benchmark | Mistral Large 3 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Coding | 1447 | 1445 |
| Aider Polyglot | — | 59.6% |
| LMArena WebDev | 1230 | — |
| SciCode | — | 42.4% |
| WeirdML | — | 41% |
Agentic & Tool Use Not comparable
Mistral Large 3: —, Qwen3 235B-A22B: 33.7 (#48)
| Benchmark | Mistral Large 3 | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 52.1% |
| Vending-Bench 2 | — | -11.34 |
Reasoning Qwen3 235B-A22B leads
Mistral Large 3: 14.6 (#314), Qwen3 235B-A22B: 15.8 (#302)
| Benchmark | Mistral Large 3 | Qwen3 235B-A22B |
|---|---|---|
| Kagi LLM Benchmark | 50.9% | 69.4% |
| LMArena Hard Prompts | 1429 | 1433 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31% |
| NYT Connections (extended) | 7.5% | — |
| ARC-AGI-1 | — | 11% |
| CritPt | — | 0% |
| Chess Puzzles | — | 12% |
| Thematic Generalization | 23% | — |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LMCA | — | 29.3% |
| Epoch Capabilities Index | — | 143.87 |
| ForecastBench | — | 59.7 |
Math Qwen3 235B-A22B leads
Mistral Large 3: 36.0 (#131), Qwen3 235B-A22B: 48.5 (#51)
| Benchmark | Mistral Large 3 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Math | 1415 | 1431 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| Omni-MATH | — | 71.8% |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3 235B-A22B leads
Mistral Large 3: 35.5 (#173), Qwen3 235B-A22B: 49.5 (#67)
| Benchmark | Mistral Large 3 | Qwen3 235B-A22B |
|---|---|---|
| Vectara Hallucination Rate | 14.5% | 9.3% |
| LMArena Expert | 1421 | 1460 |
| GPQA Diamond | — | 80.1% |
| SimpleQA Verified | — | 40.4% |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| GPQA (HELM) | — | 72.7% |
Multimodal Not comparable
Mistral Large 3: 37.6 (#65), Qwen3 235B-A22B: —
| Benchmark | Mistral Large 3 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Vision | 1222 | — |
Multilingual Too close to call
Mistral Large 3: 52.6 (#79), Qwen3 235B-A22B: 52.5 (#84)
| Benchmark | Mistral Large 3 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1412 | 1410 |
| LMArena Chinese | 1448 | 1481 |
| LMArena French | 1456 | 1445 |
| LMArena German | 1438 | 1432 |
| LMArena Japanese | 1399 | 1400 |
| LMArena Korean | 1384 | 1391 |
| LMArena Russian | 1412 | 1411 |
| LMArena Spanish | 1437 | 1429 |
Instruction Following Mistral Large 3 leads
Mistral Large 3: 74.1 (#104), Qwen3 235B-A22B: 72.8 (#132)
| Benchmark | Mistral Large 3 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1402 | 1408 |
| IFEval | — | 83.5% |
Long Context Qwen3 235B-A22B leads
Mistral Large 3: 43.1 (#102), Qwen3 235B-A22B: 46.1 (#25)
| Benchmark | Mistral Large 3 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1413 | 1426 |
| Fiction.LiveBench | — | 75% |
Writing & Preference Too close to call
Mistral Large 3: 60.2 (#100), Qwen3 235B-A22B: 59.8 (#103)
| Benchmark | Mistral Large 3 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1427 | 1419 |
| LMArena Creative Writing | 1385 | 1384 |
| EQ-Bench Creative Writing | 1412 | 1366 |
| LMArena Multi-Turn | 1429 | 1432 |
| Short-Story Creative Writing | — | 83% |
| WildBench | — | 86.6% |
Frequently asked questions
Is Mistral Large 3 better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 38.6 on the Noometry Index. Mistral Large 3 costs 3.3× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.
Which is cheaper, Mistral Large 3 or Qwen3 235B-A22B?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Qwen3 235B-A22B lists at $0.70 and $2.80.
Is Mistral Large 3 or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 43.8 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 3 does, with 262K tokens against 131K.
How many benchmarks do Mistral Large 3 and Qwen3 235B-A22B share?
20 benchmarks have published results for both models. Mistral Large 3 has 24 scored results on Noometry and Qwen3 235B-A22B has 49.