Kimi K3 (Max): benchmark results
Provider: Moonshot. Released 2026-07-16. Access: Open.
Aggregate Rating 1844 ± 6, rank #74 of 2168 rated models, from 412 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Long Context Reasoning | 88.67 | Accuracy (%) | 100 |
| AA Omniscience - Software Engineering (SWE) - C | 90 | Accuracy (%) | 100 |
| AA Omniscience - Software Engineering (SWE) - JavaScript | 78.18 | Accuracy (%) | 100 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 68 | Accuracy (%) | 100 |
| AA Omniscience - Software Engineering (SWE) - Swift | 80 | Accuracy (%) | 100 |
| AA Omniscience - Software Engineering (SWE) - TypeScript | 77.78 | Accuracy (%) | 100 |
| DeepSearchQA | 95 | Score (mixed sources) | 100 |
| E-Bench | 73.79 | Avg@3 (%; per-trial success averaged over tasks and three tr | 100 |
| E-Bench - Pass^3 | 58.82 | Pass^3 (%; tasks solved in all three trials; domain MCP tool | 100 |
| ForecastBench Baseline - Zero-Shot - Overall | 61.9 | Overall Brier Index (difficulty-adjusted, higher is better) | 100 |
| Harvey LAB-AA - Energy & Natural Resources | 98.35 | Criterion Pass Rate (%) | 100 |
| Kimi K3 Tech Report - CLIF Bench | 52.4 | Score (%) | 100 |
Interactive version: theaggregate.ai/model?slug=kimi-k3-max · How It Works · Data refreshed daily, snapshot 2026-10-20.