BenchCAD 2.1 Core (OpenAI runs, Codex): leaderboard

Metric: Core score (0-100; BenchCAD's 0-1 score x 100) on the 100 held-out BenchCAD 2.1 Core cases, OpenAI's runs in Codex. Source: openai.com. Saturation forecast: Around March 2028. 4 models tracked. Updated 18 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-6.2 AstraMax82.5#2
2GPT-6.2 SolMax73.1#10
3GPT-6 AstraMax62.6#7
4GPT-6.1 SolMax52.6#12

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Carbon, #6 Claude Opus 5.5.

Interactive version: theaggregate.ai/benchmark?slug=benchcad-2-1-core-openai-runs-codex · How It Works · Data refreshed daily, snapshot 2026-11-18.