CAE-Bench RC7 - Fixed Problems: leaderboard
Metric: Score (0-100), 24 tasks. Source: arxiv.org. Saturation forecast: Estimated already saturated. 12 models tracked. Updated 18 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-6 Astra | Medium | 100 | #7 |
| 2 | GPT-6.1 Sol | Medium | 100 | #12 |
| 3 | GPT-5.6 Luna | xHigh | 100 | #129 |
| 4 | GPT-6 Sol | Medium | 100 | #30 |
| 5 | Gemini 3.8 Flash | Medium | 98.55 | #39 |
| 6 | GPT-5.6 Sol | Medium | 97.22 | #33 |
| 7 | Gemini 4 Argon | Medium | 95.83 | #14 |
| 8 | GPT-6 Luna | Max | 91.67 | #102 |
| 9 | DeepSeek V4.1 Flash | High | 91.67 | #67 |
| 10 | Kimi K2.7 Code | Thinking | 76.29 | #195 |
| 11 | GLM-5.3 Flash | Low | 73.55 | #134 |
| 12 | Qwen 3.8 Flash | Low | 70.83 | #127 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=cae-bench-rc7-fixed-problems · How It Works · Data refreshed daily, snapshot 2026-11-18.