AI Coding Daily (Codex CLI) - Total: leaderboard
AI Coding Daily's LLM Coding Leaderboard (Povilas Korop) tests each model and reasoning setting on two code-quality projects (Laravel, React-TS; 20 points each), a bug-finding test (10 points), and four edge-case reliability projects (5 points each). This board is total points (currently out of 70) for runs in the Codex CLI harness; higher is better.
Metric: Total points (max 70). Source: aicodingdaily.com. Saturation forecast: Around February 2027. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra (High) | 66.35 | #6 (GPT-6 Astra) |
| 2 | GPT-6 Astra (Medium) | 66.03 | #6 (GPT-6 Astra) |
| 3 | GPT-6.1 Sol (High) | 66 | #7 (GPT-6.1 Sol) |
| 4 | GPT-6.1 Sol (Medium) | 65.05 | #7 (GPT-6.1 Sol) |
| 5 | GPT-6.1 Sol (Low) | 60.7 | #7 (GPT-6.1 Sol) |
| 6 | GPT-6.1 Terra (Max) | 60.41 | #15 (GPT-6.1 Terra) |
| 7 | GPT-6 Luna (Max) | 57.57 | #61 (GPT-6 Luna) |
| 8 | GPT-6.1 Terra (xHigh) | 57.01 | #15 (GPT-6.1 Terra) |
| 9 | GPT-6 Luna (xHigh) | 54.9 | #61 (GPT-6 Luna) |
| 10 | GPT-6.1 Terra (High) | 54.82 | #15 (GPT-6.1 Terra) |
| 11 | GPT-6.1 Terra (Medium) | 54.03 | #15 (GPT-6.1 Terra) |
| 12 | GPT-6 Luna (High) | 52.04 | #61 (GPT-6 Luna) |
| 13 | GPT-6 Luna (Medium) | 42.54 | #61 (GPT-6 Luna) |
No result here: #3 Claude Opus 5.5, #9 Gemini 4 Argon, #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=ai-coding-daily-codex-cli-total · How It Works · Data refreshed daily, snapshot 2026-11-05.