Agents' Last Exam (Agnes Harness): leaderboard
Metric: Overall Pass Rate (%). Source: snorkel.ai. 1 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Agnes-2.5-Pro-Beta (ALE Run: harness=Agnes%20Harness; effort=Not%20reported; source-model=Agnes-2.5-Pro-Beta) | 21.71 |
Interactive version: theaggregate.ai/benchmark?slug=agents-last-exam-agnes-harness · How It Works · Data refreshed daily, snapshot 2026-10-09.