RuneBench Skill - Firemaking
Games · 2026-02-26
RuneBench 30-minute Firemaking skill task. Agents play RuneScape through the SDK and are scored by the best real-game Firemaking XP per minute achieved in any 15-second window.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-6 Astra | 5924 |
| GPT-6.1 Sol | 4557 |
| Gemini 4 Argon | 3949 |
| Muse Spark 1.1 | 3797 |
| GPT-6 Sol | 3645 |
| Claude Opus 5.5 | 2734 |
| DeepSeek V4.1 Flash | 2734 |
| Gemini 3.8 Flash | 2734 |
| Claude Opus 5 | 2632 |
| Grok 4.5 | 2632 |
| Claude Fable 5.1 | 2531 |
| Gemini 3.5 Flash | 2227 |
| Claude Fable 5 | 2025 |
| Gemini 3.6 Flash | 1823 |
| Grok 4.7 | 1823 |
| Gemini 3.7 Flash | 1755 |
| Muse Spark 1.2 | 1721 |
| GLM-5.3 | 1620 |
| GPT-6 Luna | 1620 |
| Grok 4.6 | 1418 |
| GPT-5.6 Sol | 1417 |
| GPT-5.6 Terra | 1316 |
| DeepSeek-V4-Pro | 1125 |
| Claude Sonnet 5.5 | 1080 |
| GLM-5.2 | 855 |
| GPT-5.5 | 810 |
| Opus 4.7 | 600 |
| DeepSeek-V4-Flash-0731 | 506 |
| GPT-5.6 Luna | 425 |
| Opus 4.8 | 370 |
| GPT-5.3-Codex | 360 |
| Muse Spark 1.3 | 320 |
| Muse Wonder | 320 |
| GLM-5.3 Flash | 315 |
| Gemini 3.5 Flash-Lite | 300 |
| Kimi K2.7 Code | 300 |
| Opus 4.5 | 280 |
| Opus 4.6 | 280 |
| Sonnet 4.6 | 280 |
| Sonnet 4.5 | 260 |