# Epoch Automation Reports

> Epoch Automation Reports runs AI agents on open-ended tasks taken from Epoch AI's own work, such as graphic design, data insights and AI data center research, and has human graders score the output against Epoch's internal standards.

Canonical page: https://benchlm.ai/benchmarks/epochautomationreports

- Category: [Agentic](/agentic)
- Last updated: November 13, 2026

## About Epoch Automation Reports

- Year: 2026
- Tasks: 11 open-ended work tasks in five categories from Epoch AI's own work
- Format: Agent harness at highest reasoning setting, human rubric grading
- Difficulty: Open-ended professional research and design work
- Paper: [Epoch Automation Reports](https://epoch.ai/benchmarks/epoch-automation-reports)

The task suite currently has 11 tasks in five categories: graphic design, data insight generation, data explorer generation, AI data center research and research design. Each model runs in its own agent harness (for example Claude Code, Codex or Grok Build) at its highest reasoning setting, with the context a human contractor would get. Memory and skill writing are disabled so nothing carries over between tasks. A human grader scores each output against rubrics that reflect Epoch's quality bar; 100% means the work meets the standard Epoch expects from its own staff. BenchLM stores the average across categories and lists the category scores in each row's notes.

Epoch Automation Reports is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (6 models)

| Rank | Model | Creator | Score | Who ran it |
|------|-------|---------|-------|-----------|
| 1 | [Claude Fable 5.1](/models/claude-fable-5-1) | Anthropic | 65.3% | Run by Epoch Automation Reports |
| 2 | [GPT-6 Astra](/models/gpt-6-astra) | OpenAI | 65.1% | Run by Epoch Automation Reports |
| 3 | [Grok 4.6](/models/grok-4-6) | xAI | 59.1% | Run by Epoch Automation Reports |
| 4 | [Qwen3.8 Max](/models/qwen3-8-max) | Alibaba | 53.0% | Run by Epoch Automation Reports |
| 5 | [Kimi K3](/models/kimi-k3) | Moonshot AI | 52.4% | Run by Epoch Automation Reports |
| 6 | [Gemini 3.8 Flash](/models/gemini-3-8-flash) | Google | 42.3% | Run by Epoch Automation Reports |

## FAQ

### What are Epoch Automation Reports?

A benchmark of real tasks from Epoch AI's own work, from graphic design to AI data center research. Agents produce the work and human graders score it against Epoch's internal standards.

### Which AI agent scores best?

Claude Fable 5.1 in Claude Code (65.3%) and GPT-6 Astra in Codex (65.1%) lead, followed by Grok 4.6 in Grok Build (59.1%). Gemini 3.8 Flash in Antigravity is last at 42.3%.

## Compare Top Models on Epoch Automation Reports

- [Claude Fable 5.1 vs GPT-6 Astra](/compare/claude-fable-5-1-vs-gpt-6-astra)
- [GPT-6 Astra vs Grok 4.6](/compare/gpt-6-astra-vs-grok-4-6)
- [Grok 4.6 vs Qwen3.8 Max](/compare/grok-4-6-vs-qwen3-8-max)
- [Qwen3.8 Max vs Kimi K3](/compare/kimi-k3-vs-qwen3-8-max)