Updated daily at 05:00 UTC
- Released
- 27 Feb 2025
- Status
- Retired
- Retired
- 14 Jul 2025
- Context
- 128K
- Max output
- 16.4K
- Input per 1M tokens
- $75.00
- Output per 1M tokens
- $150.00
- Open weights
- No
- License
- proprietary
- Parameters
- —
- Knowledge cutoff
- Oct 2023
- Reasoning
- No
- Modalities
- text, image → 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 | 21.4 | Not ranked | 1 of 4 |
| Coding & software engineering | 44.9 | Not ranked | 1 of 5 |
| Vision & multimodal understanding | 17.5 | Not ranked | 1 of 3 |
| Human preference | 41.6 | Not ranked | 2 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 |
|---|---|---|---|---|---|---|
| SimpleBench | Score (AVG@5) | 34.5% | Third party | — | — | SimpleBench Leaderboard via Epoch AI |
Scientific reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GPQA Diamond | Accuracy | 68.7% | Independent | — | 28 Feb 2025 | Epoch AI |
Mathematics
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| MATH Level 5 | Accuracy | 78.6% | Independent | — | 28 Feb 2025 | Epoch AI |
| OTIS Mock AIME 2024-2025 | Accuracy | 37.8% | Independent | — | 28 Feb 2025 | Epoch AI |
Coding & software engineering
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Aider Polyglot | Percent correct | 44.9% | Third party | — | — | https://aider.chat/docs/leaderboards/ via Epoch AI |
| Cybench | Unguided challenges solved | 17.5% | Third party | — | — | Cybench leaderboard via Epoch AI |
| WeirdML (v2) | Average accuracy | 39.4% | Third party | — | — | https://htihle.github.io/weirdml.html via Epoch AI |
Long context
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Fiction.LiveBench | % correct at 16K tokens (Epoch's column) | 63.9% | Third party | — | — | Fiction.live leaderboard via Epoch AI |
Vision & multimodal understanding
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Visual Physics Comprehension Test (VPCT) | Correct | 45.0% | Third party | — | — | VPCT leaderboard via Epoch AI |
Writing
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| LLM Creative Story-Writing Benchmark V1 (Lech Mazur) | Mean rubric score (percent of the 10-point scale) | 75.6% | Third party | — | — | lechmazur/writing Github repository via Epoch AI |
Human preference
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Text Arena (arena.ai) | Arena score (Elo scale) | 1445 | Independent | — | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Votes | 14547 | Independent | — | 25 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Arena score (Elo scale) | 1225 | Independent | — | 28 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Votes | 2925 | Independent | — | 28 Sep 2026 | Arena |