MEGA-Bench Task - Crossword Mini 5x5 — leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet (20240620) | 77.1 |
| 2 | Gemini 2.5 Pro | 75 |
| 3 | Gemini 1.5 Pro (002) | 73.6 |
| 4 | Claude 3.5 Sonnet (20241022) | 69.3 |
| 5 | GPT-4o | 67.9 |
| 6 | Gemini 2.0 Flash (Preview) | 67.1 |
| 7 | Gemma 3 27B (IT) | 52.1 |
| 8 | GPT-4o Mini | 48.6 |
| 9 | Qwen 2 VL 72B | 44.3 |
| 10 | Llama 4 Scout Base | 39.3 |
| 11 | InternVL3-78B | 35 |
| 12 | Gemini 1.5 Flash (002) | 35 |
| 13 | InternVL2.5-78B | 32.9 |
| 14 | InternVL3-14B | 30.7 |
| 15 | Gemma 3 12B (IT) | 29.3 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-crossword-mini-5x5 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.