HANDBOOK.md
We show this table for reference; we do not rank on it.
An agent benchmark run through its official OpenHands-based harness.
Benchmark score on HANDBOOK.md — October 29, 2026
We compile the HANDBOOK.md rows from provider self-reports. Kimi K3.1 Pro leads the table at 44.6%. We do not use these results to rank models overall.
1 modelAgenticCurrentDisplay onlyUpdated October 29, 2026
Benchmark score table (1 model)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | Kimi K3.1 ProMoonshot AI | 44.6% | Not reported | Pending |
About HANDBOOK.md
Year
2026
Tasks
Agent tasks (v1 release)
Format
Task score
Difficulty
Advanced agentic work
Moonshot evaluates tasks from the benchmark's early open-source v1 release. BenchLM stores the provider-run value as display-only launch evidence.
Freshness and provenance
Version
HANDBOOK.md 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 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.
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 6,100+ subscribers.
One email each week. Unsubscribe anytime.