Anthropic · model
Claude Opus 5.5 (high with fallback) benchmark scores
As of 2026-10-07, Claude Opus 5.5 (high with fallback) (Anthropic) has measured scores on 5 benchmarks and estimated scores on 4 more.
| Benchmark | Score | Source |
|---|---|---|
| Terminal-Bench 2.1 | 88.2% | estimated ± 4.0 pp, high confidence |
| Terminal-Bench 4.0 | 56.6% | measured |
| Terminal-Bench Science 0.1 | 49.0% | measured |
| GPQA Diamond | 95.1% | estimated ± 1.3 pp, high confidence |
| SciCode | 60.4% | measured |
| CritPt | 30.0% | estimated ± 3.5 pp, high confidence |
| GDP.pdf | 27.6% | estimated ± 4.0 pp, high confidence |
| MMMU-Pro | 86.0% | measured |
| Humanity's Last Exam | 55.6% | measured |