Updated daily at 05:00 UTC
- Released
- 20 Aug 2025
- Status
- Current
- Context
- 524.3K
- Max output
- —
- Input per 1M tokens
- —
- Output per 1M tokens
- —
- Open weights
- Yes
- License
- apache-2.0
- Parameters
- 36B
- Knowledge cutoff
- —
- Reasoning
- Yes
- Modalities
- 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 | 8.5 | 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 | 13.0% | Independent | — | 28 Aug 2026 | Epoch AI |
| MMLU-Pro | Accuracy | 82.7% | Self-reported | — | — | EvalEval via Hugging Face Community Evals |
Scientific reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GPQA Diamond | Accuracy | 71.5% | Independent | — | 30 Aug 2026 | Epoch AI |
Mathematics
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | Accuracy | 67.5% | Independent | — | 28 Aug 2026 | Epoch AI |