Model comparison
Mistral Large vs Qwen3-VL 235B-A22B
Qwen3-VL 235B-A22B is the stronger model overall, scoring 43.2 to 31.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Mistral Large scores higher in 0 categories and Qwen3-VL 235B-A22B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3-VL 235B-A22B leads 39.0 to 18.2.
- Qwen3-VL 235B-A22B is cheaper at $0.70 / $2.80 per million input/output tokens, against $2 / $6 for Mistral Large.
Side by side
| Mistral Large | Qwen3-VL 235B-A22B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.9 | 43.2 |
| Released | 2024-02-26 | 2025-04 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 16K | 33K |
| Input $ / M tokens | $2 | $0.70 |
| Output $ / M tokens | $6 | $2.80 |
| Results tracked | 51 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-VL 235B-A22B leads
Mistral Large: 34.3 (#240), Qwen3-VL 235B-A22B: 42.4 (#100)
| Benchmark | Mistral Large | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Coding | 1277 | 1439 |
| 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: 28.6 (#89), Qwen3-VL 235B-A22B: —
| Benchmark | Mistral Large | Qwen3-VL 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |
Reasoning Qwen3-VL 235B-A22B leads
Mistral Large: 15.8 (#310), Qwen3-VL 235B-A22B: 29.3 (#92)
| Benchmark | Mistral Large | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1428 |
| SimpleBench | 22.5% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 43.5% | — |
| DTBench | 65.1% | — |
| LiveBench Data Analysis | 50.1% | — |
| LMCA | 16.7% | — |
| Epoch Capabilities Index | 128.52 | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |
Math Qwen3-VL 235B-A22B leads
Mistral Large: 18.2 (#291), Qwen3-VL 235B-A22B: 39.0 (#118)
| Benchmark | Mistral Large | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Math | 1262 | 1426 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Qwen3-VL 235B-A22B leads
Mistral Large: 30.1 (#230), Qwen3-VL 235B-A22B: 40.3 (#121)
| Benchmark | Mistral Large | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Expert | 1232 | 1442 |
| GPQA Diamond | 51.3% | — |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |
Multimodal Not comparable
Mistral Large: —, Qwen3-VL 235B-A22B: 39.8 (#55)
| Benchmark | Mistral Large | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Vision | — | 1247 |
Multilingual Qwen3-VL 235B-A22B leads
Mistral Large: 40.0 (#219), Qwen3-VL 235B-A22B: 51.9 (#97)
| Benchmark | Mistral Large | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Non-English | 1237 | 1405 |
| LMArena Chinese | 1240 | 1463 |
| LMArena French | 1325 | 1452 |
| LMArena German | 1254 | 1424 |
| LMArena Japanese | 1188 | 1385 |
| LMArena Korean | 1202 | 1394 |
| LMArena Russian | 1257 | 1408 |
| LMArena Spanish | 1268 | 1428 |
Instruction Following Qwen3-VL 235B-A22B leads
Mistral Large: 67.9 (#191), Qwen3-VL 235B-A22B: 74.2 (#101)
| Benchmark | Mistral Large | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1249 | 1406 |
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
Long Context Qwen3-VL 235B-A22B leads
Mistral Large: 38.3 (#199), Qwen3-VL 235B-A22B: 43.4 (#98)
| Benchmark | Mistral Large | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1261 | 1420 |
Writing & Preference Qwen3-VL 235B-A22B leads
Mistral Large: 40.7 (#242), Qwen3-VL 235B-A22B: 60.2 (#99)
| Benchmark | Mistral Large | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Text | 1266 | 1420 |
| LMArena Creative Writing | 1243 | 1366 |
| LMArena Multi-Turn | 1260 | 1428 |
| 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-VL 235B-A22B?
Qwen3-VL 235B-A22B is the stronger model overall, scoring 43.2 to 31.9 on the Noometry Index.
Which is cheaper, Mistral Large or Qwen3-VL 235B-A22B?
Qwen3-VL 235B-A22B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Mistral Large lists at $2 and $6.
Is Mistral Large or Qwen3-VL 235B-A22B better for coding?
Qwen3-VL 235B-A22B scores higher on coding benchmarks: 42.4 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do Mistral Large and Qwen3-VL 235B-A22B share?
17 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Qwen3-VL 235B-A22B has 18.