RuneBench Gold - Vanilla 15m
Games · 2026-02-26
RuneBench Vanilla 15m gold-accumulation task. Agents start from the default condition and are scored by the peak number of coins seen during the run.
Top models (higher is better)
| Model | Score |
|---|---|
| Opus 4.6 | 474 |
| Haiku 4.5 | 347 |
| Sonnet 4.6 | 174 |
| Opus 4.7 | 130 |
| Opus 4.5 | 103 |
| Sonnet 4.5 | 49.0 |