research benchmark
ResearchClawBench
ResearchClawBench evaluates research agents on realistic, tool-using research tasks that require code execution and filesystem workspace interaction.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
ResearchClawBench Ranking
Higher score ranks better on this benchmark.
| 01 | XI | 16.9% | 100.0% | 1 | C |
ResearchClawBench Highlights
The leading models and scores on this benchmark.
What is ResearchClawBench?
What ResearchClawBench measures and how its scores work.
ResearchClawBench evaluates research agents on realistic, tool-using research tasks that require code execution and filesystem workspace interaction.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- ResearchClawBench
- Modality
- text
- Primary category
- research
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- researchclawbench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about ResearchClawBench.
Which model scores highest on ResearchClawBench?
MiMo-V2.5 is currently ranked first with 16.9%.
What does ResearchClawBench measure?
ResearchClawBench evaluates research agents on realistic, tool-using research tasks that require code execution and filesystem workspace interaction.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.