Kimi CLI + Kimi K2.6: benchmark results
Provider: Moonshot. Access: API.
Aggregate Rating 1744 ± 50, rank #201 of 10916 rated models, from 4 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SlopCodeBench (Just Solve) | 10.7 | Strict solve rate (%): share of the 196 checkpoints whose wo | 85.3 |
| SlopCodeBench (Just Solve) - Isolated | 18.9 | Isolated solve rate (%): share of the 196 checkpoints whose | 64.7 |
| SlopCodeBench (Just Solve) - Core | 51 | Core solve rate (%): share of the 196 checkpoints whose work | 41.2 |
| SWE-Interact | 14.7 | Resolve rate (%) of 75 multi-turn software-engineering tasks | 0 |
Interactive version: theaggregate.ai/model?slug=kimi-cli-plus-kimi-k2-6 · How It Works · Data refreshed daily, snapshot 2026-11-08.