Mistral AIPixtral Large
Pixtral Large is a Mistral AI open-weights model, released 18 Nov 2024. Its best configuration ranks #615 of 785 on the BenchLeader Index at 41.9 ±1.6, in the lower half. The ± is the point: 280 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in instruction following (38) and lowest in multimodal (36). At $3.00 per million tokens blended it is pricier than most ranked models. Last measured 19 Oct 2026.
- Blended price
- $3.00/M
- $2.00 in · $6.00 out
- Output speed
- –
- First answer
- –
- Context
- 128k
- Full answer
- –
- Cost per run
- –
- Released
- 18 Nov 2024
- Overall index42
- Instruction following38
- Multimodal36
- Composite37
How its index has moved
9 Sept 2026 to 21 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. 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 | not stated | Source | Trend |
|---|---|---|---|
| GPQA Diamond (AA)not in index | 50.5%#428 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 2.8%#609 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| τ²-Bench Telecom (AA)not in index | 36.5%#230 | Artificial Analysis |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| IFBench | 34.5%#317 | Artificial Analysis |
Multimodal
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Vision | 1089#129 | Arena (LMArena) | |
| MMMU-Pro | 50.6%#239 | Artificial Analysis | |
| VISTA | 33.9%#47 | Scale AI SEAL |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA Intelligence Index v4.3.2 | 7.2#490 | 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 | – | – |
| Summarize 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 | – | – |
More from Mistral AI
See also
Questions people ask
- What are Pixtral Large's benchmark scores?
- As of 25 Oct 2026, Pixtral Large scores 41.9 ±1.6 on the BenchLeader Index, strongest in instruction following (38) and weakest in multimodal (36). That rests on 5 independent benchmark results, and every score on this page links to its publisher.
- How does Pixtral Large rank?
- Pixtral Large is #615 of 785 ranked configurations on 25 Oct 2026. 280 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does Pixtral Large cost per 1M tokens?
- As of 25 Oct 2026, Pixtral Large costs $2.00 per 1M input tokens and $6.00 per 1M output tokens, $3.00 blended (three input tokens per output token).
- When was Pixtral Large released?
- Mistral AI released Pixtral Large on 18 Nov 2024.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Pixtral Large: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/pixtral-large.