| Benchmark | Score | Top model |
|---|---|---|
| Chartography (with tools)% | 89.0% | Claude Opus 5.5 |
| CursorBench 4.0% | 57.8% | Claude Opus 5.5 |
| FrontierCode v1.1 (Main)% | 54.4% | Claude Opus 5.5 |
| GDPVal 2.1 (AA) | 1846 | Claude Opus 5.5 |
| HLE (with tools)% | 67.7% | Claude Opus 5.5 |
| OSWorld 2.0 (partial)% | 81.8% | Claude Opus 5.5 |
| Terminal Bench 4.0% | 66.4% | Claude Opus 5.5 |
| Terminal-Bench-Science 0.1% | 58.7% | GPT 6 Astra |
Figures are taken from public model cards, technical reports and vendor announcements, and are approximate where sources disagree. Results from different benchmark versions or tool-use settings never share a column: Terminal Bench 2.1, 3.0 and DeepSWE v1.1 are distinct benchmarks, and HLE with tools is separate from HLE without tools. “Top model” is the highest scoring model with a published result on that benchmark; when several models tie, all of them are listed. Benchmarks this model has no published result for are left out; the line above shows how many of the benchmarks are covered.