Atlas

Benchmarks

← All benchmarks

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)

ModelScore
GPT-5.6 Terra1250
Gemini 4 Argon1181
Claude Opus 5.51148
Grok 4.61148
Gemini 3.6 Flash1125
GPT-5.6 Sol1125
Gemini 3.7 Flash1114
Claude Fable 5.11080
Claude Fable 51080
GPT-6 Astra1080
GPT-6 Sol1050
Claude Opus 51046
GPT-5.51046
Gemini 3.8 Flash1013
GPT-6.1 Sol979
GLM-5.3875
Grok 4.5875
Laguna S 2.1875
Muse Spark 1.1875
Muse Wonder844
Gemini 3.5 Flash810
Muse Spark 1.2810
Claude Sonnet 5.5769
GLM-5.2743
DeepSeek-V4-Flash-0731700
Opus 4.7612
Grok 4.7608
Opus 4.6574
GLM-5.3 Flash574
GPT-5.6 Luna574
Gemini 3.1 Pro Preview540
Muse Spark 1.3481
GPT-5.4 Mini472
Opus 4.8469
Gemini 3.5 Flash-Lite469
Mistral Large 4 Preview463
Kimi K2.7 Code438
GPT-5.4375
Grok 4.3375
Opus 4.5350
Loading Atlas data…