Agents' Last Exam (Gemini CLI): leaderboard
Metric: Overall Pass Rate (%). Source: snorkel.ai. 1 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (ALE Run: harness=Gemini%20CLI; effort=High; source-model=Gemini%203.1%20Pro) | 16.45 |
Interactive version: theaggregate.ai/benchmark?slug=agents-last-exam-gemini-cli · How It Works · Data refreshed daily, snapshot 2026-10-09.