CLBench Life - Private Conversations: leaderboard
Metric: Task solving rate (%) on the 45 private one-on-one conversation 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 2030. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 (High) | 20.7 |
| 2 | Gemini 3.1 Pro (Preview) (High) | 17 |
| 3 | GPT-5.4 (High) | 15.6 |
| 4 | Hy3-preview (High) | 14.4 |
| 5 | DeepSeek V3.2 (Thinking) | 12.6 |
| 6 | Kimi K2.5 (High) | 12.6 |
| 7 | Grok 4.20 (High) | 11.9 |
| 8 | Seed 2.0 Pro (High) | 9.6 |
Interactive version: theaggregate.ai/benchmark?slug=clbench-life-private-conversations · How It Works · Data refreshed daily, snapshot 2026-10-07.