# Epoch Automation Reports leaderboard

external benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/external-epoch-automation-reports

Every model the catalog carries a published Epoch Automation Reports value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Agent harness at highest reasoning setting, human rubric grading |
| Tasks | 11 open-ended work tasks in five categories from Epoch AI's own work |
| Difficulty | Open-ended professional research and design work |
| Published by | [Epoch Automation Reports](https://epoch.ai/benchmarks/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.

## Epoch Automation Reports ranking

6 models with a published Epoch Automation Reports value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Agent harness at highest reasoning setting, human rubric grading | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Fable 5.1](https://modelchoice.dev/models/claude-fable-5-1) | Anthropic | 64.4 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Grok 4.6](https://modelchoice.dev/models/grok-4-6) | xAI | 59.1 | Last good 2026-11-19 · source benchlm:models |
| 3 | [GPT-6 Astra](https://modelchoice.dev/models/gpt-6-astra) | OpenAI | 55.5 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Qwen3.8 Max](https://modelchoice.dev/models/qwen3-8-max) | Alibaba | 53.0 | Last good 2026-11-19 · source benchlm:models |
| 5 | [Kimi K3](https://modelchoice.dev/models/kimi-3) | Moonshot AI | 52.4 | Last good 2026-11-19 · source benchlm:models |
| 6 | [Gemini 3.8 Flash](https://modelchoice.dev/models/gemini-3-8-flash) | Google | 42.3 | Last good 2026-11-19 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
