RuneBench Skill - Ranged
Games · 2026-02-26
RuneBench 30-minute Ranged skill task. Agents play RuneScape through the SDK and are scored by the best real-game Ranged XP per minute achieved in any 15-second window.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-6 Astra | 748 |
| Gemini 4 Argon | 600 |
| Claude Opus 5.5 | 510 |
| GPT-6.1 Sol | 492 |
| GPT-6 Sol | 398 |
| Claude Opus 5 | 376 |
| Claude Fable 5.1 | 358 |
| Gemini 3.8 Flash | 316 |
| Grok 4.6 | 316 |
| Gemini 3.7 Flash | 308 |
| Claude Fable 5 | 248 |
| Sonnet 5 | 246 |
| GPT-5.6 Terra | 246 |
| Gemini 3.5 Flash | 240 |
| Opus 4.7 | 228 |
| DeepSeek V4.1 Flash | 204 |
| Grok 4.5 | 204 |
| Claude Sonnet 5.5 | 200 |
| GLM-5.3 | 182 |
| DeepSeek-V4-Flash-0731 | 166 |
| Muse Spark 1.2 | 146 |
| GPT-5.6 Sol | 144 |
| Gemini 3 Flash Preview | 138 |
| GPT-5.5 | 134 |
| Gemini 3.6 Flash | 130 |
| Opus 4.8 | 128 |
| GPT-5.6 Luna | 122 |
| Gemini 3.1 Pro Preview | 118 |
| GLM-5.2 | 116 |
| Opus 4.6 | 114 |
| GPT-5.3-Codex | 84.0 |
| Muse Wonder | 84.0 |
| Grok 4.7 | 82.0 |
| Muse Spark 1.1 | 80.0 |
| Claude Haiku 5.5 | 64.0 |
| GPT-6 Luna | 64.0 |
| Grok 4.3 | 64.0 |
| Opus 4.5 | 62.0 |
| Gemini 3.5 Flash-Lite | 50.0 |
| Sonnet 4.5 | 42.0 |