Updated daily at 05:00 UTC
- Released
- 11 Sep 2024
- Status
- Retired
- Retired
- 31 Dec 2025
- Context
- 131.1K
- Max output
- —
- Input per 1M tokens
- $0.15
- Output per 1M tokens
- $0.15
- Open weights
- Yes
- License
- apache-2.0
- Parameters
- 12B
- Knowledge cutoff
- —
- Reasoning
- No
- Modalities
- image, text → text
Category scores
Out of 100, from independent and third-party results only, by method category-2026-09-29.1.
| Category | Score | Rank | Coverage |
|---|---|---|---|
| Vision & multimodal understanding | 37.0 | Not ranked | 1 of 3 |
| Human preference | 10.4 | Not ranked | 1 of 5 |
Benchmark results
Every result we hold for this model, with who ran it and where it was published.
Vision & multimodal understanding
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GeoBench | Country accuracy | 37.0% | Third party | — | — | GeoBench leaderboard via Epoch AI |
Human preference
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Vision Arena (arena.ai) | Arena score (Elo scale) | 1025 | Independent | — | 28 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Votes | 7511 | Independent | — | 28 Sep 2026 | Arena |
Other Pixtral versions
- Pixtral Large18 Nov 2024