agents benchmark
MM-ClawBench
MM-ClawBench evaluates models on MiniMax's Claw-style agent benchmark, measuring practical agentic task completion quality in real-world OpenClaw usage scenarios.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
MM-ClawBench Ranking
Higher score ranks better on this benchmark.
| 01 | MI | 62.7% | 100.0% | 1 | C |
MM-ClawBench Highlights
The leading models and scores on this benchmark.
What is MM-ClawBench?
What MM-ClawBench measures and how its scores work.
MM-ClawBench evaluates models on MiniMax's Claw-style agent benchmark, measuring practical agentic task completion quality in real-world OpenClaw usage scenarios.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MM-ClawBench
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mm-clawbench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MM-ClawBench.
Which model scores highest on MM-ClawBench?
MiniMax M2.7 is currently ranked first with 62.7%.
What does MM-ClawBench measure?
MM-ClawBench evaluates models on MiniMax's Claw-style agent benchmark, measuring practical agentic task completion quality in real-world OpenClaw usage scenarios.
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.