On 2026-11-01, the YZ Index Smoke test covered 13 models, and Claude Opus 4.7 ranked first for the day with 98.79 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 Ranking
| Rank | Model | Main Leaderboard | Code Execution | Material Constraints | Integrity |
|---|---|---|---|---|---|
| #1 | Claude Opus 4.7 | 98.79 | 97.8 | 100 | pass |
| #2 | GPT-6 Astra | 97.25 | 95 | 100 | pass |
| #3 | GPT-6 Luna | 90.93 | 94.3 | 86.8 | pass |
| #4 | Claude Sonnet 4.6 | 86.38 | 95.6 | 75.1 | pass |
| #5 | GPT-6.1 Sol | 86 | 95 | 75 | pass |
| #6 | GPT-6 Sol | 85.62 | 94.3 | 75 | pass |
| #7 | Grok 4 | 82.75 | 78.2 | 88.3 | pass |
| #8 | GPT-o3 | 77.49 | 89.1 | 63.3 | pass |
| #9 | GPT-5.5 | 69.06 | 75 | 61.8 | pass |
| #10 | Gemini 3.1 Pro | 61 | 70 | 50 | pass |
| #11 | Doubao Pro | 59.9 | 78.8 | 36.8 | pass |
| #12 | DeepSeek V4 Pro | 50.05 | 50 | 50.1 | pass |
| #13 | Gemini 2.5 Pro | 50 | 50 | 50 | pass |
Key Changes
- DeepSeek V4 Pro: main leaderboard down 34.8 points, code execution −44 points, material constraints −23.6 points
- Gemini 3.1 Pro: main leaderboard down 29.4 points, code execution −24 points, material constraints −35.9 points
- Doubao Pro: main leaderboard down 28.6 points, material constraints −60.2 points
- Gemini 2.5 Pro: main leaderboard down 28.1 points, code execution −31.3 points, material constraints −24.2 points
- Claude Opus 4.7: main leaderboard up 15.8 points, code execution +28.8 points
Signals to Watch
- Grok 4: code execution plunged −15.8 points
- GPT-o3: material constraints plunged −25 points
- GLM-4.6: incomplete data (missing judgment and communication dimensions due to API failure/timeout); an automatic re-run has been scheduled, and it is not included in this period's ranking
- Gemini 3.1 Pro: main leaderboard plunged −29.4 points
- Doubao Pro: main leaderboard plunged −28.6 points
- DeepSeek V4 Pro: main leaderboard plunged −34.8 points
- Gemini 2.5 Pro: main leaderboard plunged −28.1 points
- Qwen3 Max: incomplete data (missing several evaluation dimensions due to API failure/timeout); an automatic re-run has been scheduled, and it is not included in this period's ranking
When reading this kind of Smoke brief, the focus should be on two questions: first, whether a model reveals the same type of weakness on consecutive days; second, whether its integrity rating moves from pass to warn or fail. Large single-day changes in execution or constraint scores may stem from question sampling, or may be an early signal of genuine degradation, and need to be verified by follow-up runs.
Data source: YZ Index | Run #405 | View raw data
© 2026 Winzheng.com 赢政天下 | 转载请注明来源并附原文链接