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 | DeepSeek V4.1-Flash 1017 | 72.1% | 2026-10-20 |
Nothing has been overwritten yet.