Anthropic
claude-opus-4-20250514
Made by Anthropic. Released 2025-05-22. Accessibility not recorded. Cheapest standard rate we hold: $75 per million output tokens, no context split.
What it costs
| Tier | Kind | In | Out | Cached in | From |
|---|---|---|---|---|---|
| standard | text | $15 | $75 | $1.50 | licensed-index |
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 |
|---|---|---|---|---|
| frontiermath | Epoch AI | 0.0±0.01 | 2025-08-05 | 27K |
| frontiermath | Epoch AI | 0.0±0.01 | 2025-07-04 | — |
| frontiermath tier 4 | Epoch AI | 0.0±0.00 | 2025-07-01 | — |
| frontiermath tier 4 | Epoch AI | 0.0±0.03 | 2025-07-01 | 27K |
| gpqa diamond | Epoch AI | 0.8±0.03 | 2025-05-22 | 16K |
| gpqa diamond | Epoch AI | 0.7±0.03 | 2025-05-22 | — |
| math level 5near its ceiling | Epoch AI | 0.9±0.01 | 2025-05-22 | — |
| otis mock aime 2024 2025near its ceiling | Epoch AI | 0.6±0.07 | 2025-05-28 | 27K |
| otis mock aime 2024 2025near its ceiling | Epoch AI | 0.6±0.07 | 2025-05-22 | 16K |
| otis mock aime 2024 2025near its ceiling | Epoch AI | 0.4±0.07 | 2025-05-22 | — |
| swe bench verified | Epoch AI | 0.7±0.02 | 2026-02-06 | — |
| aider polyglot | collected by Epoch AI | 70.7 | — | — |
| aider polyglot | collected by Epoch AI | 72.0 | — | 32K |
| algotune | collected by Epoch AI | 1.3 | — | unknown |
| arc aginear its ceiling | collected by Epoch AI | 0.4 | — | 16K |
| arc aginear its ceiling | collected by Epoch AI | 0.3 | — | 1K |
| arc aginear its ceiling | collected by Epoch AI | 0.3 | — | 8K |
| arc aginear its ceiling | collected by Epoch AI | 0.2 | — | — |
| arc agi 2 | collected by Epoch AI | 0.0 | — | 1K |
| arc agi 2 | collected by Epoch AI | 0.0 | — | 8K |
| arc agi 2 | collected by Epoch AI | 0.1 | — | 16K |
| arc agi 2 | collected by Epoch AI | 0.0 | — | — |
| critpt | collected by Epoch AI | 0.0 | — | unknown |
| cybench | collected by Epoch AI | 0.4 | — | — |
| deepresearchbench | collected by Epoch AI | 0.5 | — | 2K |
| dtbenchnear its ceiling | collected by Epoch AI | 0.8 | — | unknown |
| enigma eval | collected by Epoch AI | 0.1 | — | unknown |
| fictionlivebench | collected by Epoch AI | 0.4 | — | — |
| forecastbench | collected by Epoch AI | 61.1 | — | unknown |
| geobench | collected by Epoch AI | 2915 | — | 32K |
| gso | collected by Epoch AI | 0.1 | — | OpenHands |
| hle | collected by Epoch AI | 0.1 | — | unknown |
| lech mazur writing | collected by Epoch AI | 8.4 | — | 16K |
| lech mazur writing | collected by Epoch AI | 8.3 | — | — |
| lmca | collected by Epoch AI | 37.4 | — | unknown |
| metr time horizons | collected by Epoch AI | 100 | — | unknown |
| metr time horizons | collected by Epoch AI | 85.6 | — | 16K |
| simplebench | collected by Epoch AI | 0.6 | — | unknown |
| simplebench | collected by Epoch AI | 0.6 | — | 12K |
| vpct | collected by Epoch AI | 0.4 | — | 16K |
| vpct | collected by Epoch AI | 0.3 | — | — |
| weirdml | collected by Epoch AI | 0.4 | — | 16K |
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.
What retires, and when
- deprecation — 2026-06-15 (Retired)
Every rate we hold · Why there is no single best model · Everything from Anthropic