Anthropic
availableShows if the model has enough results for an index.Claude Opus 4
Claude Opus 4 is a model from Anthropic. 14 benchmarks count toward its score, in 6 categories.
IndexOverall score out of 100.44.2 ±5.3
CoverageShare of the index weight with results.90%
SpeedOutput tokens per second.—
Input / 1MUS dollars per 1M input tokens.N/A
Output / 1MUS dollars per 1M output tokens.N/A
ContextMaximum tokens in one request.N/A
EloLMArena rating and rank.1366 (#178)
The index is a score out of 100. The ± range shows how much it can change.
42,845 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category, out of 100.
Out of 100Results
14 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result as a score out of 100. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| MGSM | Multilingual | 93.8% | — | — | 9 Jan 2026 | Vals AI |
| MATH 500 | Math | 90.4% | 42.8 | — | 9 Jan 2026 | Vals AI |
| MMLU Pro | Knowledge | 86.2% | 56.3 | — | 1 Sept 2026 | Vals AI |
| MATH level 5 | Math | 85.0% | 40.5 | — | — | Epoch AI |
| τ²-bench Retail | Agentic | 81.4% | 57.2 | Anthropic | 30 Apr 2026 | Sierra Research |
| MMMU Pro | Multimodal | 73.3% | 46.6 | — | 1 Sept 2026 | Vals AI |
| GPQA diamond | Knowledge | 72.7% | 45.4 | — | — | Epoch AI |
| GPQA Diamond | Knowledge | 71.7% | 44.5 | — | 1 Sept 2026 | Vals AI |
| SWE-Bench verified | Coding | 70.7% | 54.2 | — | — | Epoch AI |
| LiveCodeBench | Coding | 62.6% | 41.3 | — | 1 Sept 2026 | Vals AI |
| OTIS Mock AIME 2024-2025 | Math | 60.0% | 45.1 | — | — | Epoch AI |
| τ²-bench Airline | Agentic | 59.6% | 41.6 | Anthropic | 2 Mar 2026 | Sierra Research |
| AIME | Math | 41.3% | 32.9 | — | 16 Apr 2026 | Vals AI |
| ARC-AGI-1 (semi-private) | Reasoning | 22.5% | 37.8 | — | — | ARC Prize Foundation |
| FrontierMath-2025-02-28-Private | Math | 4.3% | 34.7 | — | — | Epoch AI |
| FrontierMath-Tier-4-2025-07-01-Private | Math | 2.1% | 45.7 | — | — | Epoch AI |
| ARC-AGI-2 (semi-private) | Reasoning | 1.3% | 40.4 | — | — | ARC Prize Foundation |
14 benchmarks count, from 16 of 17 results. A grey row does not count. Too few models took that benchmark.