Atlas

Benchmarks

← All benchmarks

RuneBench Skill - Fletching

Games · 2026-02-26

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

Top models (higher is better)

ModelScore
GPT-6 Astra3065
Claude Opus 5.51950
Grok 4.71452
GPT-6.1 Sol1235
Gemini 4 Argon1125
Claude Fable 51079
GPT-5.51041
Grok 4.5937
Grok 4.6937
GPT-6 Sol900
GPT-5.6 Terra825
Opus 4.8758
Muse Wonder758
Gemini 3.6 Flash750
Muse Spark 1.1750
Claude Sonnet 5.5675
Claude Fable 5.1581
Gemini 3.8 Flash581
Gemini 3.5 Flash498
GPT-5.6 Luna450
Claude Opus 5415
DeepSeek V4.1 Flash394
Gemini 3.7 Flash375
GPT-5.4374
Gemini 3 Flash Preview332
Opus 4.7225
Qwen3.7-Max (source unspecified)225
GLM-5.2221
GPT-5.6 Sol175
GPT-6 Luna150
GLM-5.3125
Opus 4.6120
Gemini 3.1 Pro Preview120
Sonnet 5100
Opus 4.594.0
DeepSeek-V4-Flash-073182.0
DeepSeek-V4-Pro79.0
GLM-5.3 Flash75.0
Kimi K370.0
Gemini 3 Pro Preview67.0
Loading Atlas data…