Benchmark
ResearchClawBench
ResearchClawBench evaluates research agents on realistic, tool-using research tasks that require code execution and filesystem workspace interaction.
- Modality
- text
- Categories
- research, agents, tool_calling
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 1
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| MiMo-V2.5 | Xiaomi | 0.1691 | 2026-04-22 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.