A2Z GameSpec-Bench - Adaptive Playtest Big: leaderboard
Metric: Adaptive Playtest Big (%; coding-agent game design fidelity; Table 2). Source: a2z-gamespec-bench.github.io. Saturation forecast: Around January 2027. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Fable 5.1 | 74.7 |
| 2 | Claude Opus 5 | 67.7 |
| 3 | GPT-6 Astra | 67.4 |
| 4 | GPT-5.5 | 61.7 |
| 5 | GPT-5.6 Sol | 57.9 |
| 6 | Claude Opus 4.8 | 46 |
| 7 | GLM-5.3 | 40.4 |
| 8 | DeepSeek V4 Pro | 27 |
Interactive version: theaggregate.ai/benchmark?slug=a2z-gamespec-bench-adaptive-playtest-big · How It Works · Data refreshed daily, snapshot 2026-10-10.