GameCraft-Bench — leaderboard
Metric: Overall Score. Source: tongxuluo.github.io. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Fable 5 | 65.7 |
| 2 | GPT-5.6 Sol | 60.5 |
| 3 | Claude Opus 4.7 | 41.46 |
| 4 | GPT-5.5 | 39.49 |
| 5 | Kimi K2.6 | 30.65 |
| 6 | MiMo-V2.5-Pro | 24.1 |
| 7 | GLM-5.1 | 18.29 |
| 8 | MiniMax-M2.7 | 10.95 |
| 9 | DeepSeek V4 Pro | 2.15 |
Interactive version: aibenchmarks.dev/benchmark?slug=gamecraft-bench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.