Kimi K3 Tech Report - Kimi Code Bench 2.0 (Claude Code): leaderboard
Moonshot AI's in-house Kimi Code Bench 2.0 evaluates code agents on end-to-end software engineering tasks across many languages and production stacks; here every model runs in the Claude Code harness. Kimi K3 technical report, Table 3; score in percent, higher is better. Claude Fable 5's 76.9 involved 13 fallbacks and 1 refusal out of 80 tasks.
Metric: Score (%). Source: raw.githubusercontent.com. Saturation forecast: Around February 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5 (Max) | 76.9 | #20 (Claude Fable 5) |
| 2 | Kimi K3 (Max) | 73.7 | #35 (Kimi K3) |
| 3 | Claude Opus 4.8 (Max) | 71.7 | #39 (Claude Opus 4.8) |
| 4 | GLM-5.2 (Max) | 64.2 | #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-kimi-code-bench-2-0-claude-code · How It Works · Data refreshed daily, snapshot 2026-11-05.