MEGA-Bench Task - Chess Puzzles Checkmate: leaderboard
The "Chess Puzzles Checkmate" subtask of MEGA-Bench Task. A single task from MEGA-Bench, a large-scale multimodal evaluation suite that scores vision-language models across 500+ real-world tasks spanning perception, reasoning, OCR, charts, documents, and multi-image understanding.
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 0 | #343 |
| 2 | Gemma 3 27B (IT) | 0 | #523 |
| 3 | Gemma 3 12B (IT) | 0 | #664 |
| 4 | Gemma 3 4B (IT) | 0 | #992 |
| 5 | GPT-4o Mini | 0 | #599 |
| 6 | Claude 3.5 Sonnet (20241022) | 0 | #291 |
| 7 | InternVL3-8B | 0 | #620 |
| 8 | Gemini 1.5 Pro (002) | 0 | #349 |
| 9 | Gemini 1.5 Flash (002) | 0 | #583 |
| 10 | Claude 3.5 Sonnet (20240620) | 0 | #299 |
| 11 | InternVL3-38B | 0 | #405 |
| 12 | InternVL3-78B | 0 | #352 |
| 13 | Gemini 2.5 Pro (Preview 03-25) | 0 | #123 |
| 14 | InternVL2-8B | 0 | #817 |
| 15 | MiniCPM-V-2.6 | 0 | #836 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-chess-puzzles-checkmate · How It Works · Data refreshed daily, snapshot 2026-10-20.