Atlas

Benchmarks

← All benchmarks

RuneBench Skill - Strength

Games · 2026-02-26

RuneBench 30-minute Strength skill task. Agents play RuneScape through the SDK and are scored by the best real-game Strength XP per minute achieved in any 15-second window.

Top models (higher is better)

ModelScore
GPT-6.1 Sol6875
GPT-6 Sol524
Claude Opus 5.5510
Claude Fable 5.1428
GPT-5.6 Sol356
Gemini 3.7 Flash352
Gemini 4 Argon336
GLM-5.3336
Grok 4.5334
Muse Spark 1.1320
Claude Sonnet 5.5298
Claude Fable 5280
Gemini 3.8 Flash274
Claude Opus 5258
Grok 4.6242
Kimi K2.7 Code240
Grok 4.7226
Gemini 3.5 Flash-Lite224
GPT-6 Astra224
Opus 4.8210
Muse Spark 1.3210
DeepSeek-V4-Flash-0731208
Sonnet 4.5204
Gemini 3 Flash Preview198
Gemini 3.6 Flash194
Kimi K2.6194
GPT-5.6 Terra186
GPT-5.5184
GLM-5.2182
Gemini 3.5 Flash180
GPT-5.6 Luna180
Qwen3.7-Max (source unspecified)178
Gemini 3.1 Pro Preview176
GLM-5.3 Flash176
DeepSeek-V4-Pro166
Muse Spark 1.2166
Qwen3.8 27B166
Muse Wonder164
Opus 4.6162
GPT-6 Luna138
Loading Atlas data…