MEGA-Bench Task - ILI Ratio Future Prediction — leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet (20240620) | 34 |
| 2 | Gemini 1.5 Pro (002) | 26.9 |
| 3 | Claude 3.5 Sonnet (20241022) | 23.9 |
| 4 | InternVL3-38B | 18.1 |
| 5 | Gemini 2.0 Flash (Preview) | 16.1 |
| 6 | GPT-4o | 12.5 |
| 7 | Gemini 2.5 Pro | 11.6 |
| 8 | Gemini 1.5 Flash (002) | 11.6 |
| 9 | InternVL3-8B | 10.2 |
| 10 | Llama 4 Scout Base | 9 |
| 11 | InternVL3-78B | 6.3 |
| 12 | Gemma 3 4B (IT) | 5.6 |
| 13 | Qwen 2 VL 72B | 5.3 |
| 14 | Gemma 3 27B (IT) | 3.9 |
| 15 | InternVL2.5-78B | 2.2 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-ili-ratio-future-prediction · How the rankings work · Data refreshed daily, snapshot 2026-07-22.