CLBench Life - Creation & Revision Histories: leaderboard
CL-bench Life (2026) tests whether language models can learn from long, messy real-life context to solve human-written tasks, a task counting as solved only when every expert rubric item is met. This board is the task solving rate in percent on tasks over document edit histories and revision suggestions; higher is better.
Metric: Task solving rate (%) on the 45 creation and revision history 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 August 2028. 10 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 4.6 | High | 20 | #113 |
| 2 | Gemini 3.1 Pro (Preview) | High | 18.5 | #99 |
| 3 | Hy3-preview | High | 14.4 | #322 |
| 4 | Kimi K2.5 | High | 13.3 | #266 |
| 5 | GPT-5.4 | High | 12.6 | #135 |
| 6 | Seed 2.0 Pro | High | 11.9 | #222 |
| 7 | Qwen 3.5 Plus | High | 11.9 | #242 |
| 8 | Grok 4.20 | High | 9.6 | #301 |
| 9 | DeepSeek V3.2 | Thinking | 6.7 | #419 |
| 10 | MiniMax-M2.5 | Thinking | 4.4 | #600 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=clbench-life-creation-revision-histories · How It Works · Data refreshed daily, snapshot 2026-11-21.