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

#ModelSettingScoreOverall rank
1Seed 2.0 ProHigh23#226
2GPT-5.4High20.7#138
3Claude Opus 4.6High16.3#114
4Hy3-previewHigh14.4#320
5Qwen 3.5 PlusHigh13.3#250
6Gemini 3.1 Pro (Preview)High10.4#102
7Grok 4.20High10.4#307
8Kimi K2.5High9.6#272
9DeepSeek V3.2Thinking7.4#425
10MiniMax-M2.5Thinking4.4#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.