# HANDBOOK.md

> An agent benchmark run through its official OpenHands-based harness.

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

- Category: [Agentic](/agentic)
- Last updated: October 29, 2026

## About HANDBOOK.md

- Year: 2026
- Tasks: Agent tasks (v1 release)
- Format: Task score
- Difficulty: Advanced agentic work
- Paper: [Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence](https://www.kimi.ai/blog/kimi-k3-1-pro)

Moonshot evaluates tasks from the benchmark's early open-source v1 release. BenchLM stores the provider-run value as display-only launch evidence.

HANDBOOK.md 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 K3.1 Pro](/models/kimi-3-1-pro) | Moonshot AI | 44.6% |

## FAQ

### What does HANDBOOK.md measure?

An agent benchmark run through its official OpenHands-based harness.

### Which model scores highest on HANDBOOK.md?

Kimi K3.1 Pro by Moonshot AI currently leads with a score of 44.6% on HANDBOOK.md.

### How many models are evaluated on HANDBOOK.md?

1 AI models have published results on HANDBOOK.md in the BenchLM catalog.

### Does HANDBOOK.md affect BenchLM's overall score?

Not directly. HANDBOOK.md is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.