Agents' Last Exam v1.1 - Muse Code 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. Muse Code; Pass Rate. Metric: Pass Rate (%).

Metric: Pass Rate (%). Source: agents-last-exam.org. 1 models tracked.

Top models

#ModelScoreOverall rank
1muse-wonder-1.0 (ALE Run: harness=Muse%20Code; effort=high; source-model=muse-wonder-1.0)36.89

Interactive version: theaggregate.ai/benchmark?slug=agents-last-exam-v1-1-muse-code-pass-rate · How It Works · Data refreshed daily, snapshot 2026-10-27.