Learn2Play Bench - Mean: leaderboard
Learn2Play Bench's average score over all scored episodes (5 per normal game, 10 per challenge game) rather than each trial's peak, so a model that needs many failed episodes to learn a game's hidden rules scores lower here than on Max; same 20 games, OpenCode harness and reference-ceiling normalization.
Metric: Normalized Mean (% of each game's reference ceiling, challenge games weighted 3). Source: liushiliushi.github.io. Saturation forecast: Around February 2028. 11 models tracked. Updated 19 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 61 | #9 | |
| 2 | GPT-6 Astra | Medium | 56.1 | #10 |
| 3 | Claude Opus 5 | 53.8 | #26 | |
| 4 | Gemini 3.5 Flash | 52.2 | #108 | |
| 5 | Qwen 3.8 Max | 51.1 | #66 | |
| 6 | Kimi K3 | 50.2 | #61 | |
| 7 | GPT-5.6 Sol | 41.1 | #36 | |
| 8 | Gemini 3.7 Flash | 39.9 | #42 | |
| 9 | DeepSeek V4 Pro | 38.2 | #198 | |
| 10 | Claude Sonnet 5 | 35.6 | #118 | |
| 11 | GPT-5 Mini | 22.3 | #365 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=learn2play-bench-mean · How It Works · Data refreshed daily, snapshot 2026-11-20.