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…
- Modality
- text
- Categories
- agents, code
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 1
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| MiniMax M2.7 | MiniMax | 0.627 | 2026-03-18 | 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.