Benchmarks · agentic
Epoch Automation Reports
Uses Epoch's equal-weight average of category rubric scores, including human-intervention deductions. Score: mean category rubric score. Collected by Jake Boggs' benchmark dashboard.
6 models · 6 results · data as of 2026-10-29 · epoch.ai ↗
Leaderboard
Fable 5.1 max
All results
6 rows| # | Model | Effort | Epoch Automation Reports |
|---|---|---|---|
| 1 | Fable 5.1 | max | 65.3% |
| 2 | GPT-6 Astra | max | 65.1% |
| 3 | Grok 4.6 | max | 59.1% |
| 4 | Qwen 3.8 Max | max | 53.0% |
| 5 | Kimi K3 | max | 52.4% |
| 6 | Gemini 3.8 Flash | max | 42.3% |