RuneBench Skill - Woodcutting
Games · 2026-02-26
RuneBench 30-minute Woodcutting skill task. Agents play RuneScape through the SDK and are scored by the best real-game Woodcutting XP per minute achieved in any 15-second window.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-5.6 Terra | 1250 |
| Gemini 4 Argon | 1181 |
| Claude Opus 5.5 | 1148 |
| Grok 4.6 | 1148 |
| Gemini 3.6 Flash | 1125 |
| GPT-5.6 Sol | 1125 |
| Gemini 3.7 Flash | 1114 |
| Claude Fable 5.1 | 1080 |
| Claude Fable 5 | 1080 |
| GPT-6 Astra | 1080 |
| GPT-6 Sol | 1050 |
| Claude Opus 5 | 1046 |
| GPT-5.5 | 1046 |
| Gemini 3.8 Flash | 1013 |
| GPT-6.1 Sol | 979 |
| GLM-5.3 | 875 |
| Grok 4.5 | 875 |
| Laguna S 2.1 | 875 |
| Muse Spark 1.1 | 875 |
| Muse Wonder | 844 |
| Gemini 3.5 Flash | 810 |
| Muse Spark 1.2 | 810 |
| Claude Sonnet 5.5 | 769 |
| GLM-5.2 | 743 |
| DeepSeek-V4-Flash-0731 | 700 |
| Opus 4.7 | 612 |
| Grok 4.7 | 608 |
| Opus 4.6 | 574 |
| GLM-5.3 Flash | 574 |
| GPT-5.6 Luna | 574 |
| Gemini 3.1 Pro Preview | 540 |
| Muse Spark 1.3 | 481 |
| GPT-5.4 Mini | 472 |
| Opus 4.8 | 469 |
| Gemini 3.5 Flash-Lite | 469 |
| Mistral Large 4 Preview | 463 |
| Kimi K2.7 Code | 438 |
| GPT-5.4 | 375 |
| Grok 4.3 | 375 |
| Opus 4.5 | 350 |