Anthropic
availableShows if the model has enough results for an index.Claude Opus 4.1
Claude Opus 4.1 is a model from Anthropic. 17 benchmarks count toward its score, in 6 categories.
IndexOverall score. 50 is the middle.46.8 ±4.9
CoverageShare of the index weight with results.90%
SpeedOutput tokens per second.10/s
Input / 1MUS dollars per 1M input tokens.$15 batch $7.5
Output / 1MUS dollars per 1M output tokens.$75 batch $37.5 US dollars per 1M output tokens in a batch.
ContextMaximum tokens in one request.200K
EloLMArena rating and rank.1418 (#112)
50 is the middle of the board. The range shows the doubt in the index. Batch work costs less.
75,913 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category. 50 is the middle.
50 is the middleResults
17 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result on the index scale. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| MGSM | Multilingual | 94.2% | — | — | 9 Jan 2026 | Vals AI |
| MATH 500 | Math | 93.0% | 45.7 | — | 9 Jan 2026 | Vals AI |
| MMLU Pro | Knowledge | 87.2% | 58.0 | — | 1 Sept 2026 | Vals AI |
| τ²-bench Retail | Agentic | 82.4% | 57.9 | Anthropic | 30 Apr 2026 | Sierra Research |
| GPQA diamond | Knowledge | 76.8% | 49.1 | — | — | Epoch AI |
| MMMU Pro | Multimodal | 73.7% | 47.3 | — | 1 Sept 2026 | Vals AI |
| SWE-Bench verified | Coding | 73.3% | 56.4 | — | — | Epoch AI |
| GPQA Diamond | Knowledge | 70.0% | 42.8 | — | 1 Sept 2026 | Vals AI |
| LiveCodeBench | Coding | 64.6% | 43.0 | — | 1 Sept 2026 | Vals AI |
| OTIS Mock AIME 2024-2025 | Math | 64.4% | 47.6 | — | — | Epoch AI |
| τ²-bench Airline | Agentic | 56.0% | 39.0 | Anthropic | 2 Mar 2026 | Sierra Research |
| AIME | Math | 44.2% | 34.3 | — | 16 Apr 2026 | Vals AI |
| Mystery Game Puzzles | Reasoning | 21.0% | 56.3 | — | — | Epoch AI |
| FrontierMath-Tiers-1-3-v2-Private | Math | 12.6% | 38.6 | — | — | Epoch AI |
| IOI v1 | Coding | 12.5% | 47.1 | — | 9 Aug 2026 | Vals AI |
| EBR-bench | Reasoning | 7.9% | 54.8 | — | — | Epoch AI |
| Chess Puzzles | Reasoning | 7.0% | 32.6 | — | — | Epoch AI |
| FrontierMath-2025-02-28-Private | Math | 6.6% | 36.7 | — | — | Epoch AI |
| FrontierMath-Tier-4-2025-07-01-Private | Math | 4.2% | 48.0 | — | — | Epoch AI |
| FrontierMath-Tier-4-v2-Private | Math | 2.4% | 49.1 | — | — | Epoch AI |
17 benchmarks count, from 19 of 20 results. A grey row does not count. Too few models took that benchmark.