Agents' Last Exam v1.1 - ALE-Claw Pass Rate: leaderboard
ALE v1.1, 122 tasks. Native harness/model/effort roster without selecting strongest effort. Pass rate counts perfect-score runs; partial-credit score averages graded scores over all 122 tasks, including zero for failed/missing runs. Timeouts retain graded scores. Separate from legacy ALE v1. ALE-Claw; Pass Rate. Metric: Pass Rate (%).
Metric: Pass Rate (%). Source: agents-last-exam.org. 1 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | gemini-4-argon (ALE Run: harness=ALE-Claw; effort=high; source-model=gemini-4-argon) | 37.7 |
Interactive version: theaggregate.ai/benchmark?slug=agents-last-exam-v1-1-ale-claw-pass-rate · How It Works · Data refreshed daily, snapshot 2026-10-27.