LLM Stats (AutomationBench; Public (DeepSeek minimal harness)): leaderboard
LLM Stats source-attributed result collection. Protocol: Public (DeepSeek minimal harness). Scores and source method notes retained without rescaling beyond the published percent conversion. Unverified protocols remain separate source observations; they are not assumed equivalent to another model or benchmark setting.
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Around February 2028. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek V4 Pro (0813) | 31.8 | #53 |
| 2 | DeepSeek-V4-Flash-Vision-Exp | 25.7 | #79 |
| 3 | DeepSeek V4 Flash (0731) | 25.1 | #75 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-automationbench-public-deepseek-minimal-harness · How It Works · Data refreshed daily, snapshot 2026-10-16.