Mistral AIPixtral Large (latest)
Best configuration ranks #468 of 610 on the BenchLeader Index at 42.2 ±1.4. Last measured 27 Aug 2026. Released 1 Nov 2024.
- Blended price
- $3.00/M
- $2.00 in · $6.00 out
- Output speed
- –
- First answer
- –
- Context
- 128k
- Overall index42
- Instruction following38
- Multimodal37
- Composite38
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| GPQA Diamond (AA)not in index | 50.5%#405 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 2.8%#518 | Artificial Analysis |
Agents & tools
| Benchmark | default | Source |
|---|---|---|
| τ²-Bench Telecom (AA)not in index | 36.5%#223 | Artificial Analysis |
Instruction following
| Benchmark | default | Source |
|---|---|---|
| IFBench | 34.5%#302 | Artificial Analysis |
Multimodal
| Benchmark | default | Source |
|---|---|---|
| LMArena Vision | 1089#110 | LMArena |
| MMMU-Pro | 50.6%#204 | Artificial Analysis |
| VISTA | 33.9%#47 | Scale AI SEAL |
Composite
| Benchmark | default | Source |
|---|---|---|
| AA Intelligence Index | 7.2#410 | Artificial Analysis |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0026 | – | – |
| Summarise a 30-page report | 12,000 / 600 | $0.028 | – | – |
| Code edit | 6,000 / 1,500 | $0.021 | – | – |
| Agentic coding session | 60,000 / 4,000 | $0.144 | – | – |
| Structured extraction | 2,000 / 200 | $0.0052 | – | – |
See also
Data as of 9 Sept 2026. Compare with another model.