Fangcun DeepSeek 1017 Report - RE-Bench Restricted LLM valid diagnostic loss: leaderboard
Fangcun independent report 2610.35671v1, Oct 4–25 2026 hosted API evaluations; source Table A.1 resolves all seven full model names. Temperature 1, top_p 0.95, maximum reasoning effort unless explicitly overridden; GLM 5.3 rubric judge. API/format failures excluded according to source; not locally deployed weights or uncensored variants. Restricted LLM missing-word prediction loss with primitive-operation constraints. Source marks Flash 1017/Flash as rule-violating, V4 Flash incomplete verification, Gemini unchanged baseline. Those diagnostic values are retained in review only; board includes the 3 verified rule-compliant model submissions. Metric: Diagnostic loss.
Metric: Diagnostic loss. Source: arxiv.org. Saturation forecast: Around 2028. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra (Max) | 3.6 | #3 (GPT-6 Astra) |
| 2 | DeepSeek V4 Pro (Max) | 4.04 | #109 (DeepSeek V4 Pro) |
| 3 | GPT-5.6 Sol (Max) | 5.08 | #19 (GPT-5.6 Sol) |
No result here: #2 Claude Opus 5.5, #6 GPT-6.1 Sol, #8 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=fangcun-deepseek-1017-report-re-bench-restricted-llm-valid-diagnostic-loss · How It Works · Data refreshed daily, snapshot 2026-10-28.