Hi Moonshot AI team,

This PR adds the ResearchClawBench overall evaluation result for Kimi-K2.5.

ResearchClawBench is an end-to-end scientific research benchmark for evaluating AI agents and LLMs on tasks that require reading task data and related work, writing and executing code, producing figures, and generating publication-style reports. Final reports are scored against expert checklists derived from human-authored target papers.

The run was executed with ResearchHarness, using tools enabled, code execution, and a file-system workspace. The submitted value is the overall mean score out of 100 over completed ResearchClawBench tasks:

• Model: Kimi-K2.5
• Score: 13.96 / 100
• Completed tasks: 39/40
• Run date: 2026-04-15
• Benchmark task id: overall

The detailed leaderboard is available here: https://internscience.github.io/ResearchClawBench-Home/

Thank you!