CLBench Life - Game Logs: leaderboard
Metric: Task solving rate (%) on the 45 game-log (match replays, hand histories, gameplay commentary) tasks of CL-bench Life; a task is solved only when the response satisfies every human-written binary rubric item, judged by GPT-5.1 at high reasoning effort from the response and rubrics alone; reasoning mode at high effort where the model supports it, mean of three runs; higher is better. Source: arxiv.org. Saturation forecast: Around April 2028. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) (High) | 34.1 |
| 2 | GPT-5.4 (High) | 30.4 |
| 3 | Seed 2.0 Pro (High) | 24.4 |
| 4 | Hy3-preview (High) | 23.3 |
| 5 | Claude Opus 4.6 (High) | 17.8 |
| 6 | Kimi K2.5 (High) | 17.8 |
| 7 | Grok 4.20 (High) | 15.6 |
| 8 | DeepSeek V3.2 (Thinking) | 12.6 |
Interactive version: theaggregate.ai/benchmark?slug=clbench-life-game-logs · How It Works · Data refreshed daily, snapshot 2026-10-07.