BOTTLED - MAVE: leaderboard
Metric: F1 (0-1). Source: arxiv.org. Saturation forecast: Around May 2027. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5 | 0.46 |
| 2 | GLM-5.3 | 0.43 |
| 3 | GPT-5.6 Terra | 0.41 |
| 4 | GLM-5.3 Flash | 0.34 |
| 5 | Gemini 3.1 Pro (Preview) | 0.29 |
| 6 | Qwen 3.8 Max | 0.25 |
| 7 | GPT-5.6 Sol | 0.18 |
| 8 | Qwen 3.8 Flash | 0.16 |
| 9 | Claude Sonnet 5 | 0.15 |
| 10 | Gemini 3.1 Flash Lite | 0 |
Interactive version: theaggregate.ai/benchmark?slug=bottled-mave · How It Works · Data refreshed daily, snapshot 2026-10-09.