Benchmarks · creative
MineBench
Models turn a text prompt into raw Minecraft-style block coordinates; humans vote pairwise on the rendered builds. Value is the conservative rankScore (rating − 2·RD), not raw Elo.
77 models · 77 results · data as of 2026-10-29 · minebench.ai ↗
Leaderboard
GPT-6 Astra Pro max
More from this benchmark
6 published measuresScore vs any published measure6 measures: sub-scores, splits, counts
Breakdown
darker is better within each column · click a column to sort| Model | ||||
|---|---|---|---|---|
| GPT-6 Astra Pro max | 4,126 | 844 | 395 | 6,653 |
| Gemini 4 Argon max | 911 | 333 | 81 | 1,714 |
| GPT-6.1 Sol Pro | 1,886 | 911 | 310 | 3,774 |
| Opus 5.5 max, fallback | 2,169 | 1,070 | 276 | 4,294 |
| GPT-6 Sol Pro max | 1,961 | 1,056 | 213 | 3,971 |
| Opus 5 max | 4,517 | 3,071 | 659 | 11,593 |
| Kimi K3.1 max | 494 | 111 | 25 | 935 |
| Sonnet 5.5 max, fallback | 1,894 | 991 | 163 | 3,680 |
| GPT-5.6 Sol Pro max | 4,626 | 3,144 | 737 | 11,833 |
| Fable 5.1 max, fallback | 2,778 | 1,797 | 298 | 6,239 |
| GPT-5.5 Pro xhigh | 7,332 | 4,134 | 1,046 | 17,698 |
| Fable 5 max | 7,207 | 3,659 | 672 | 16,011 |
| Muse Wonder (Max) | 483 | 250 | 25 | 972 |
| Grok 4.7 max | 444 | 172 | 11 | 949 |
| GPT-5.5 xhigh | 6,811 | 5,362 | 1,016 | 18,519 |
| DeepSeek V4.1 Flash max | 2,003 | 902 | 129 | 4,102 |
| Grok 4.6 max | 1,746 | 1,476 | 174 | 4,612 |
| Gemini 3.8 Flash max | 2,063 | 930 | 132 | 3,930 |
| GPT-5.4 Pro xhigh | 9,735 | 4,738 | 889 | 22,134 |
| Opus 4.8 max | 5,813 | 3,242 | 455 | 13,406 |
| GLM 5.3 Flash max | 1,871 | 882 | 112 | 3,868 |
| Gemini 3.7 Flash max | 1,643 | 966 | 143 | 3,882 |
| GLM 5.3 max | 2,179 | 979 | 129 | 4,938 |
| GPT-6 Luna Pro max | 1,288 | 719 | 62 | 2,510 |
| Muse Spark 1.3 max | 2,173 | 923 | 103 | 4,356 |
All results
77 rows| # | Model | Effort | MineBench |
|---|---|---|---|
| 1 | GPT-6 Astra Pro | max | 2240 ±16 |
| 2 | Gemini 4 Argon | max | 2214 ±26 |
| 3 | GPT-6.1 Sol Pro | 2180 ±18 | |
| 4 | Opus 5.5 | max | 2149 ±17 |
| 5 | GPT-6 Sol Pro | max | 2078 ±16 |
| 6 | Opus 5 | max | 2017 ±11 |
| 7 | Kimi K3.1 | max | 2013 ±37 |
| 8 | Sonnet 5.5 | max | 2007 ±16 |
| 9 | GPT-5.6 Sol Pro | max | 2002 ±11 |
| 10 | Fable 5.1 | max | 1936 ±13 |
| 11 | GPT-5.5 Pro | xhigh | 1929 ±9 |
| 12 | Fable 5 | max | 1876 ±9 |
| 13 | Muse Wonder (Max) | max | 1870 ±31 |
| 14 | Grok 4.7 | max | 1859 ±34 |
| 15 | GPT-5.5 | xhigh | 1853 ±9 |
| 16 | DeepSeek V4.1 Flash | max | 1828 ±17 |
| 17 | Grok 4.6 | max | 1820 ±14 |
| 18 | Gemini 3.8 Flash | max | 1812 ±16 |
| 19 | GPT-5.4 Pro | xhigh | 1801 ±8 |
| 20 | Opus 4.8 | max | 1792 ±9 |
| 21 | GLM 5.3 Flash | max | 1789 ±17 |
| 22 | Gemini 3.7 Flash | max | 1772 ±16 |
| 23 | GLM 5.3 | max | 1768 ±16 |
| 24 | GPT-6 Luna Pro | max | 1752 ±20 |
| 25 | Muse Spark 1.3 | max | 1752 ±17 |
| 26 | Kimi K3 | max | 1718 ±15 |
| 27 | GPT-5.6 Luna Pro | 1711 ±18 | |
| 28 | Gemini 3.1 Pro | high | 1683 ±8 |
| 29 | GPT-5.4 | xhigh | 1673 ±8 |
| 30 | Gemini 3.5 Flash | xhigh | 1659 ±10 |