Public Artificial Intelligence Benchmark Records Database
Claude 3 Sonnet
MODEL RECORD: ANTHR-S3
Table may be scrolled horizontally on narrow displays.
| Record No. | Model | Benchmark | Metric | Score | Eval Date | Source | Model ID |
|---|---|---|---|---|---|---|---|
BR-002S3-001 |
Claude 3 Sonnet | Artificial Analysis Intelligence Index | Overall | 4.7 | Unknown | Primary source | ANTHR-S3 |
BR-002S3-002 |
Claude 3 Sonnet | GPQA Diamond | Accuracy | 40% | Unknown | Primary source | ANTHR-S3 |
BR-002S3-003 |
Claude 3 Sonnet | Humanity's Last Exam No tools | Overall | 3.8% | Unknown | Primary source | ANTHR-S3 |
BR-002S3-004 |
Claude 3 Sonnet | SciCode | Overall | 22.9% | Unknown | Primary source | ANTHR-S3 |
Showing records 1–4 of 4
Page 1 of 1