CLBench Life - Community Interactions: 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 forum, comment-section and social-media threads; higher is better.
Metric: Task solving rate (%) on the 45 community-interaction (forum, comment and social media thread) 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 October 2028. 10 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Seed 2.0 Pro | High | 23 | #226 |
| 2 | GPT-5.4 | High | 20.7 | #138 |
| 3 | Claude Opus 4.6 | High | 16.3 | #114 |
| 4 | Hy3-preview | High | 14.4 | #320 |
| 5 | Qwen 3.5 Plus | High | 13.3 | #250 |
| 6 | Gemini 3.1 Pro (Preview) | High | 10.4 | #102 |
| 7 | Grok 4.20 | High | 10.4 | #307 |
| 8 | Kimi K2.5 | High | 9.6 | #272 |
| 9 | DeepSeek V3.2 | Thinking | 7.4 | #425 |
| 10 | MiniMax-M2.5 | Thinking | 4.4 | #600 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=clbench-life-community-interactions · How It Works · Data refreshed daily, snapshot 2026-11-22.