Updated daily at 05:00 UTC
- Released
- 30 Jul 2026
- Status
- Current
- Context
- 262.1K
- Max output
- —
- Input per 1M tokens
- —
- Output per 1M tokens
- —
- Open weights
- Yes
- License
- apache-2.0
- Parameters
- 276B, 12B active
- Knowledge cutoff
- —
- Reasoning
- Yes
- Modalities
- text, image, audio → 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 | 13.7 | Not ranked | 1 of 4 |
| Factuality & hallucination | 19.1 | 60 | 1 of 1 |
| Human preference | 42.2 | 41 | 3 of 5 |
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 | 18.0% | Independent | xhigh | 14 Aug 2026 | Epoch AI |
| Humanity's Last Exam (HLE) | Accuracy | 31.6% | Self-reported | — | — | Model Card via Hugging Face Community Evals |
| Mystery Game Puzzles | Puzzles solved | 6.0% | Independent | xhigh | 15 Aug 2026 | Epoch AI |
Scientific reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GPQA Diamond | Accuracy | 88.5% | Independent | xhigh | 14 Aug 2026 | Epoch AI |
| GPQA Diamond | Accuracy | 89.5% | Self-reported | — | — | Model Card via Hugging Face Community Evals |
Mathematics
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| FrontierMath Tier 4 | Accuracy | 17.1% | Independent | xhigh | 14 Aug 2026 | Epoch AI |
| FrontierMath Tiers 1-3 | Accuracy | 46.3% | Independent | xhigh | 14 Aug 2026 | Epoch AI |
| OTIS Mock AIME 2024-2025 | Accuracy | 90.0% | Independent | xhigh | 14 Aug 2026 | Epoch AI |
Factuality & hallucination
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| SimpleQA Verified | Accuracy (% correct) | 19.1% | Independent | xhigh | 27 Aug 2026 | Epoch AI |
Human preference
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Code Arena: WebDev (arena.ai) | Arena score (Elo scale) | 1408 | Independent | — | 25 Sep 2026 | Arena |
| Code Arena: WebDev (arena.ai) | Votes | 5441 | Independent | — | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Arena score (Elo scale) | 1405 | Independent | — | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Votes | 24758 | Independent | — | 25 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Arena score (Elo scale) | 1207 | Independent | — | 28 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Votes | 6658 | Independent | — | 28 Sep 2026 | Arena |
Other Inkling versions
- Inkling15 Jul 2026