# Kimi Claw 24/7 Bench (Kimi Claw 24/7)

> A Moonshot AI internal long-horizon agent benchmark for persistent professional coworking tasks.

Canonical page: https://benchlm.ai/benchmarks/kimiclaw247

- Category: [Agentic](/agentic)
- Last updated: September 27, 2026

## About Kimi Claw 24/7

- Year: 2026
- Tasks: 17 professional scenarios, 610 evaluation points
- Format: Average pass rate across repeated OpenClaw runs
- Difficulty: Long-horizon agentic work
- Paper: [Kimi K2.7 Code](https://huggingface.co/moonshotai/Kimi-K2.7-Code)

Moonshot describes Kimi Claw 24/7 Bench as an in-house benchmark spanning 17 professional scenarios and 610 evaluation points across software engineering, ML research, recruiting, trading, and marketing. BenchLM stores the provider-reported exact value as display-only launch evidence.

Kimi Claw 24/7 is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (1 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Kimi K2.7 Code](/models/kimi-k2-7-code) | Moonshot AI | 46.9% |

## FAQ

### What does Kimi Claw 24/7 measure?

A Moonshot AI internal long-horizon agent benchmark for persistent professional coworking tasks.

### Which model scores highest on Kimi Claw 24/7?

Kimi K2.7 Code by Moonshot AI currently leads with a score of 46.9% on Kimi Claw 24/7.

### How many models are evaluated on Kimi Claw 24/7?

1 AI models have been evaluated on Kimi Claw 24/7 on BenchLM.

### Does Kimi Claw 24/7 affect BenchLM's overall score?

Not directly. Kimi Claw 24/7 is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.