Benchmark scores get restated when harnesses change or models are re-run. This page keeps the trail instead of quietly overwriting it.
No historical snapshots recorded yet — the current scores are shown below.
| # | Model | Score | Observed |
|---|---|---|---|
| 1 | Claude Opus 5.5 | 89% | 2026-10-20 |
| 2 | Claude Opus 5 | 84% | 2026-10-19 |
| 3 | DeepSeek V4.1-Flash 1017 | 83% | 2026-10-20 |
| 4 | GPT 5.6-Sol | 79.9% | 2026-10-19 |
| 5 | DeepSeek V4.1-Flash 0910 | 78.9% | 2026-10-19 |
| 6 | Kimi K3 | 68.1% | 2026-10-19 |
Nothing has been overwritten yet.