Agentic benchmark
MM-ClawBench leaderboard
Every model the catalog carries a published MM-ClawBench value for, ranked by that value.
CategoryAgentic
MeasureAgent workflow evaluation
TasksOpenClaw-style real-world tasks
DifficultyBroad real-world agentic execution
Published byMiniMax M2.7: Early Echoes of Self-Evolution
An OpenClaw-derived agent benchmark covering practical work and life tasks such as office document delivery, research, planning, and code maintenance.
MM-ClawBench ranking
2 models with a published MM-ClawBench value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Agent workflow evaluation |
|---|---|---|---|
| 1 |  MiniMax M2.7 | MiniMax | 62.7 |
| 2 |  MiMo-V2.5 | Xiaomi | 23.8 |
Evidence key: Observed
Rows are ordered by the value MiniMax M2.7: Early Echoes of Self-Evolution published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.