Public Artificial Intelligence Benchmark Records Database
Claude 3 Opus
MODEL RECORD: ANTHR-O3
Table may be scrolled horizontally on narrow displays.
| Record No. | Model | Benchmark | Metric | Score | Eval Date | Source | Model ID |
|---|---|---|---|---|---|---|---|
BR-002O3-001 |
Claude 3 Opus | Artificial Analysis Intelligence Index | Overall | 11.8 | Unknown | Primary source | ANTHR-O3 |
BR-002O3-002 |
Claude 3 Opus | GPQA Diamond | Accuracy | 48.9% | Unknown | Primary source | ANTHR-O3 |
BR-002O3-003 |
Claude 3 Opus | Humanity's Last Exam No tools | Overall | 3.1% | Unknown | Primary source | ANTHR-O3 |
BR-002O3-004 |
Claude 3 Opus | SciCode | Overall | 23.3% | Unknown | Primary source | ANTHR-O3 |
Showing records 1–4 of 4
Page 1 of 1