Vector Eval - DROP — leaderboard
Metric: Mean Score (%). Source: huggingface.co. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet | 89.78 |
| 2 | Llama 3.1 70B Instruct | 88.11 |
| 3 | Gemini 1.5 Pro | 88.01 |
| 4 | GPT-4o Mini | 80.66 |
| 5 | GPT-4o | 75.12 |
| 6 | Gemini 1.5 Flash | 75.1 |
| 7 | Command-R+ | 74.36 |
| 8 | Mistral Large 2 (Jul) | 74.24 |
Interactive version: theaggregate.ai/benchmark?slug=vector-eval-drop · How the rankings work · Data refreshed daily, snapshot 2026-07-22.