A2Z GameSpec-Bench - Scenario Replay Big: leaderboard
Metric: Scenario Replay Big (%; coding-agent game design fidelity; Table 2). Source: a2z-gamespec-bench.github.io. Saturation forecast: Around March 2028. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Fable 5.1 | 55.1 |
| 2 | Claude Opus 5 | 54.4 |
| 3 | GPT-6 Astra | 52.1 |
| 4 | GPT-5.6 Sol | 48.3 |
| 5 | GPT-5.5 | 42.5 |
| 6 | Claude Opus 4.8 | 41.4 |
| 7 | GLM-5.3 | 34.5 |
| 8 | DeepSeek V4 Pro | 25.9 |
Interactive version: theaggregate.ai/benchmark?slug=a2z-gamespec-bench-scenario-replay-big · How It Works · Data refreshed daily, snapshot 2026-10-10.