MM-ClawBench
We show this table for reference; we do not rank on it.
An OpenClaw-derived agent benchmark covering practical work and life tasks such as office document delivery, research, planning, and code maintenance.
Benchmark score on MM-ClawBench — September 27, 2026
We compile the MM-ClawBench rows from provider self-reports. MiniMax M2.7 leads the table at 62.7%, followed by MiMo-V2.5 (23.8%). We do not use these results to rank models overall.
MiniMax M2.7
MiniMax
MiMo-V2.5
Xiaomi
2 modelsAgenticCurrentDisplay onlyUpdated September 27, 2026
Benchmark score table (2 models)
ScoreAbout MM-ClawBench
Year
2026
Tasks
OpenClaw-style real-world tasks
Format
Agent workflow evaluation
Difficulty
Broad real-world agentic execution
MiniMax built MM-ClawBench from commonly used OpenClaw tasks to evaluate how well models handle broad real-world agent scenarios across work and personal productivity.
Freshness and provenance
Version
MM-ClawBench 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does MM-ClawBench measure?
An OpenClaw-derived agent benchmark covering practical work and life tasks such as office document delivery, research, planning, and code maintenance.
Which model scores highest on MM-ClawBench?
MiniMax M2.7 by MiniMax currently leads with a score of 62.7% on MM-ClawBench.
How many models are evaluated on MM-ClawBench?
2 AI models have been evaluated on MM-ClawBench on BenchLM.
Compare top models on MM-ClawBench
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 2,000+ readers.
One email each week. Unsubscribe anytime.