Kimi K3.1 Pro Tech Blog - GDP.pdf w/ python: leaderboard
Moonshot KimiK3.1Pro release evaluations; explicit max header, Kimi temperature1/top-p0.95 except specified overrides. Original PDF in IPython sandbox; Gemini3.5Flash Medium officialrubricjudge; task-macro criterionpassrate; five runs. Task-macro rubric pass rate (%). Copied third-party comparator results are not re-ingested; source-specific harness retained.
Metric: Task-macro rubric pass rate (%). Source: www.kimi.com. Saturation forecast: Around March 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra (Max) | 85.5 | #6 (GPT-6 Astra) |
| 2 | Claude Opus 5.5 (Max) | 83.9 | #4 (Claude Opus 5.5) |
| 3 | Claude Fable 5.1 (Max) | 83.8 | #9 (Claude Fable 5.1) |
| 4 | DeepSeek V4.1 Flash (1017) (Max) | 73 | #25 (DeepSeek V4.1 Flash (1017)) |
No result here: #7 GPT-6.1 Sol, #8 Gemini 4 Argon, #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=kimi-k3-1-pro-tech-blog-gdp-pdf-w-python · How It Works · Data refreshed daily, snapshot 2026-10-24.