Epoch
DeepSeek-R1-0528
Made by DeepSeek. Released 2025-05-28. Accessibility not recorded. Cheapest standard rate we hold: $2.15 per million output tokens, no context split.
What it costs
| Tier | Kind | In | Out | Cached in | From |
|---|---|---|---|---|---|
| standard | text | $0.50 | $2.15 | $0.35 | registry |
per million tokens, US dollars. * marks a rate from a single registry or two that disagree — the best available number rather than a confirmed one. Every other row is confirmed against a seller or a licensed index.
What it scores, by house
| Benchmark | House | Score | Evaluated | Scaffold |
|---|---|---|---|---|
| gpqa diamond | Epoch AI | 0.8±0.02 | 2025-05-29 | — |
| math level 5near its ceiling | Epoch AI | 1.0±0.00 | 2025-05-29 | — |
| otis mock aime 2024 2025near its ceiling | Epoch AI | 0.7±0.05 | 2025-05-29 | — |
| aider polyglot | collected by Epoch AI | 71.4 | — | — |
| ale bench | collected by Epoch AI | 804 | — | — |
| arc aginear its ceiling | collected by Epoch AI | 0.2 | — | — |
| arc agi 2 | collected by Epoch AI | 0.0 | — | — |
| deepresearchbench | collected by Epoch AI | 0.4 | — | — |
| lech mazur writing | collected by Epoch AI | 8.2 | — | — |
| metr time horizons | collected by Epoch AI | 31.2 | — | — |
| simplebench | collected by Epoch AI | 0.4 | — | — |
| weirdml | collected by Epoch AI | 0.4 | — | — |
These scores are not comparable between houses and are not added up. A score is dated by when it was evaluated, not when the model was released, and a score without its scaffold is not a measurement — which is why both are printed.
Every rate we hold · Why there is no single best model · Everything from Epoch