CAE-Bench RC7 - Varying Physical Inputs: leaderboard

Metric: Score (0-100), 56 tasks. Source: arxiv.org. Saturation forecast: Around July 2027. 12 models tracked. Updated 18 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-6.1 SolMedium50.35#12
2GPT-6 AstraMedium49.79#7
3Gemini 4 ArgonMedium48.2#14
4GPT-5.6 SolMedium44.37#33
5GPT-5.6 LunaMax43.56#129
6GPT-6 LunaxHigh42.25#102
7Gemini 3.8 FlashMedium41.06#39
8GPT-6 SolMedium39.9#30
9DeepSeek V4.1 FlashHigh32.73#67
10Qwen 3.8 FlashLow30.16#127
11Kimi K2.7 CodeThinking24.85#195
12GLM-5.3 FlashLow21.38#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-varying-physical-inputs · How It Works · Data refreshed daily, snapshot 2026-11-18.