Kimi K3 Tech Report - KAET: leaderboard
Kimi Autonomous Execution Tasks (KAET), a Moonshot AI in-house benchmark of long-horizon autonomous execution on tasks simulating real user requests and enterprise system operations. Kimi K3 technical report, Table 3; score in percent, higher is better. Kimi K3 ran in Kimi Code, Claude models and GLM-5.2 in Claude Code, GPT models in Codex.
Metric: Score (%). Source: raw.githubusercontent.com. Saturation forecast: Around February 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol (Max) | 85.4 | #22 (GPT-5.6 Sol) |
| 2 | Kimi K3 (Max) | 83.5 | #35 (Kimi K3) |
| 3 | GPT-5.5 (xHigh) | 79.7 | #33 (GPT-5.5) |
| 4 | Claude Opus 4.8 (Max) | 78.7 | #39 (Claude Opus 4.8) |
| 5 | GLM-5.2 (Max) | 74.7 | #80 (GLM-5.2) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=kimi-k3-tech-report-kaet · How It Works · Data refreshed daily, snapshot 2026-11-05.