CAE-Bench RC7 - Overall: leaderboard
Metric: Score (0-100), equal weight over 80 tasks. Source: arxiv.org. Saturation forecast: Around February 2027. 12 models tracked. Updated 18 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-6.1 Sol | Medium | 65.24 | #12 |
| 2 | GPT-6 Astra | Medium | 64.85 | #7 |
| 3 | Gemini 4 Argon | Medium | 62.49 | #14 |
| 4 | GPT-5.6 Sol | Medium | 60.23 | #33 |
| 5 | GPT-5.6 Luna | Max | 59.32 | #129 |
| 6 | Gemini 3.8 Flash | Medium | 58.3 | #39 |
| 7 | GPT-6 Sol | Medium | 57.93 | #30 |
| 8 | GPT-6 Luna | xHigh | 56.35 | #102 |
| 9 | DeepSeek V4.1 Flash | High | 50.41 | #67 |
| 10 | Qwen 3.8 Flash | Low | 42.36 | #127 |
| 11 | Kimi K2.7 Code | Thinking | 40.28 | #195 |
| 12 | GLM-5.3 Flash | Low | 37.03 | #134 |
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-overall · How It Works · Data refreshed daily, snapshot 2026-11-18.