Agents' Last Exam v1.1 - Antigravity CLI Partial Credit: leaderboard
Average graded score (%) reported by ALE v1.1 for the Antigravity CLI harness on its 122-task split. Native model and reasoning-effort configurations remain separate without selecting the strongest run. The leaderboard does not specify how missing or failed evaluations enter this average. Separate from legacy ALE v1.
Metric: Partial Credit (%). Source: agents-last-exam.org. Saturation forecast: Rough model projection: around 2026. 1 model tracked. Updated 15 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | gemini-4-hydrogen | ALE run: effort=xhigh | 70.58 |
Interactive version: theaggregate.ai/benchmark?slug=agents-last-exam-v1-1-antigravity-cli-partial-credit · How It Works · Data refreshed daily, snapshot 2026-11-16.