The 2026-11-08 YZ Index Smoke quick test covered 13 models, with GPT-6 Astra ranking first for the day at 90.64 points. Smoke is a daily 10-question quick test suited to observing short-term signals; it is not equivalent to the conclusions of the weekly Full leaderboard.
This Smoke evaluation covered only two main-leaderboard dimensions: Code Execution and Material Constraints. The main leaderboard formula is 0.55 × Code Execution + 0.45 × Material Constraints. Because the daily sample size is small, single-day scores are better treated as monitoring signals rather than as long-term verdicts on model capability.
Daily Rankings
| Rank | Model | Main Leaderboard | Code Execution | Material Constraints | Integrity |
|---|---|---|---|---|---|
| #1 | GPT-6 Astra | 90.64 | 100 | 79.2 | pass |
| #2 | GPT-6.1 Sol | 89.65 | 100 | 77 | pass |
| #3 | GPT-6 Luna | 86.23 | 88.3 | 83.7 | pass |
| #4 | GPT-6 Sol | 84.97 | 82.4 | 88.1 | pass |
| #5 | Grok 4 | 77.57 | 64.7 | 93.3 | pass |
| #6 | Claude Sonnet 4.6 | 72.32 | 57.6 | 90.3 | pass |
| #7 | GPT-5.5 | 68.56 | 57.4 | 82.2 | pass |
| #8 | GPT-o3 | 63.44 | 44.4 | 86.7 | warn |
| #9 | Doubao Pro | 59.56 | 53.3 | 67.2 | warn |
| #10 | Gemini 3.1 Pro | 56.18 | 25.8 | 93.3 | pass |
| #11 | Claude Opus 4.7 | 55.3 | 26 | 91.1 | pass |
| #12 | Gemini 2.5 Pro | 52 | 20 | 91.1 | pass |
| #13 | DeepSeek V4 Pro | 50.74 | 25 | 82.2 | pass |
Key Changes
- Claude Opus 4.7: Main leaderboard down 23.6 points, Code Execution −44 points
- Gemini 3.1 Pro: Main leaderboard down 23.1 points, Code Execution −49.2 points, Material Constraints +8.8 points
- Doubao Pro: Main leaderboard down 20 points, Code Execution −43.5 points, Material Constraints +8.7 points, Integrity pass→warn
- GPT-o3: Main leaderboard down 19.5 points, Code Execution −47.2 points, Material Constraints +14.4 points, Integrity pass→warn
- GPT-5.5: Main leaderboard down 13.9 points, Code Execution −42.4 points, Material Constraints +20.9 points
Signals to Watch
- No publishable anomaly signals were retained for this run.
When reading this kind of Smoke brief, the focus should be on two questions: first, whether a given model shows the same type of weakness across consecutive days; second, whether its Integrity rating moves from pass into warn or fail. Large single-day swings in execution or constraint scores may stem from question sampling, or they may be early signals of genuine degradation, which requires follow-up runs to confirm.
Data source: YZ Index | Run #417 | View raw data
© 2026 Winzheng.com 赢政天下 | 转载请注明来源并附原文链接