MEGA-Bench Task - Exchange Rate Estimate Plot — leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 98.7 |
| 2 | Claude 3.5 Sonnet (20240620) | 98.4 |
| 3 | Qwen 2 VL 72B | 98.1 |
| 4 | Pixtral-12B | 98 |
| 5 | InternVL2.5-78B | 97.9 |
| 6 | GPT-4o | 97.6 |
| 7 | Claude 3.5 Sonnet (20241022) | 97.4 |
| 8 | Gemini 2.0 Flash (Preview) | 97.3 |
| 9 | Gemma 3 27B (IT) | 97.2 |
| 10 | Gemini 1.5 Pro (002) | 97.1 |
| 11 | Gemma 3 12B (IT) | 96.4 |
| 12 | Gemini 1.5 Flash (002) | 96.2 |
| 13 | InternVL3-14B | 95.9 |
| 14 | GPT-4o Mini | 95.1 |
| 15 | Qwen 2 VL 7B | 94 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-exchange-rate-estimate-plot · How the rankings work · Data refreshed daily, snapshot 2026-07-22.