Rankings / Anthropic
Claude 3 Opus
released 2024-03-04
BenchAtlas Index
as of 2026-07-14
base configuration
rank #417
8 families · 4 categories · medium
Benchmark evidence
12 results
coding
| LiveCodeBench v6 implementation=artificial-analysis | 27.9 % | independent | Artificial Analysis | |
| SciCode | 23.3 % | independent | Artificial Analysis |
external indices
| AA Coding Index | 19.5 points | independent | Artificial Analysis | |
| Intelligence Index v4.1 | 11.8 points | independent | Artificial Analysis |
factuality
| MASK | 79.0 % 77.7–80.3 | independent | Scale Labs |
knowledge science
| GPQA Diamond implementation=artificial-analysis | 48.9 % | independent | Artificial Analysis | |
| Humanity's Last Exam implementation=artificial-analysis | 3.1 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=artificial-analysis | 69.6 % | independent | Artificial Analysis |
multimodal
| VISTA | 27.8 % 27.3–28.4 | independent | Scale Labs |
reasoning math
| AIME implementation=artificial-analysis | 3.3 % | independent | Artificial Analysis | |
| EnigmaEval | 0.8 % 0.4–1.3 | independent | Scale Labs | |
| MATH-500 implementation=artificial-analysis | 64.1 % | independent | Artificial Analysis |