Updated daily at 05:00 UTC
- Released
- 18 Sep 2025
- Status
- Retired
- Retired
- 31 Jul 2026
- Context
- 131.1K
- Max output
- —
- Input per 1M tokens
- —
- Output per 1M tokens
- —
- Open weights
- Yes
- License
- apache-2.0
- Parameters
- 24B
- Knowledge cutoff
- —
- Reasoning
- Yes
- 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 |
|---|---|---|---|
| Knowledge & reasoning | 0.0 | Not ranked | 1 of 4 |
Benchmark results
Every result we hold for this model, with who ran it and where it was published.
Knowledge & reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Chess Puzzles | Puzzles solved | 3.0% | Independent | — | 30 Aug 2026 | Epoch AI |
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 61.3% | Third party | — | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
Scientific reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GPQA Diamond | Accuracy | 47.6% | Independent | — | 30 Aug 2026 | Epoch AI |
Mathematics
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | Accuracy | 28.1% | Independent | — | 30 Aug 2026 | Epoch AI |
Other Magistral versions
- Magistral Medium 1.218 Sep 2025
- Magistral Medium 1.124 Jul 2025
- Magistral Small 1.124 Jul 2025
- Magistral Medium 1.010 Jun 2025
- Magistral Small 1.010 Jun 2025