CLBench Life - Self-Tracking Trajectories: 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 long-term fitness, health and learning logs; higher is better.

Metric: Task solving rate (%) on the 45 self-tracking trajectory (fitness, health and learning logs) 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. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-5.4High10.4#135
2Kimi K2.5High8.9#266
3Seed 2.0 ProHigh8.1#222
4Claude Opus 4.6High7.4#113
5Hy3-previewHigh6.7#322
6DeepSeek V3.2Thinking5.9#419
7Qwen 3.5 PlusHigh5.9#242
8Gemini 3.1 Pro (Preview)High5.2#99
9Grok 4.20High3.7#301
10MiniMax-M2.5Thinking3#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-self-tracking-trajectories · How It Works · Data refreshed daily, snapshot 2026-11-21.