CLE - Codex Trial 1 Level 2: leaderboard
Full Continual Learning Exam: one serial stream of 120 professional tasks, five levels each (600 levels), in fixed order. Trial 1 permits one submission per level; Trial 2 permits one feedback-guided revision. Unreached levels fail. Lk is cumulative clearance through level k. DeepSeek V4 Flash grades the human-authored rubrics. Harness/provider default effort is unspecified. These are the full exam results, not the 20-task CLE Lite release. Harness: Codex; trial: t1. Metric: Cumulative pass rate (%).
Metric: Cumulative pass rate (%). Source: haoyu-zhao.github.io. Saturation forecast: Around October 2028. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol | 32.5 | #19 |
| 2 | GPT-5.6 Terra | 31.67 | #38 |
| 3 | GPT-5.6 Luna | 25.83 | #76 |
No result here: #5 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=cle-codex-trial-1-level-2 · How It Works · Data refreshed daily, snapshot 2026-10-26.