Eval Anything — leaderboard
Metric: Overall score. Source: huggingface.co. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 1.5 Pro | 4.58 |
| 2 | GPT-4o | 3.92 |
| 3 | Qwen2-Audio-7B-Instruct | 2.73 |
| 4 | Qwen 2 VL 7B Instruct | 2.62 |
| 5 | Llama 3.1 8B Instruct | 2.14 |
Interactive version: theaggregate.ai/benchmark?slug=eval-anything · How the rankings work · Data refreshed daily, snapshot 2026-07-22.