OpenVLM AI2D - Moon Phase and Equinox — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 284 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | InternVL3-78B | 81.2 |
| 2 | Gemini 2.5 Pro | 80.1 |
| 3 | GPT-5 (2025-08-07) | 80.1 |
| 4 | Qwen 2 VL 72B | 78.7 |
| 5 | InternVL2.5-78B | 78.7 |
| 6 | InternVL3-38B | 78 |
| 7 | InternVL3-14B | 75.8 |
| 8 | GPT-5 Mini (2025-08-07) | 75.8 |
| 9 | InternVL3-8B | 74 |
| 10 | Ovis2-8B | 73.3 |
| 11 | GPT-4o ChatGPT | 72.6 |
| 12 | Qwen 2 VL 7B | 72.2 |
| 13 | InternVL2-8B | 71.8 |
| 14 | GPT-4.1 (2025-04-14) | 71.8 |
| 15 | GPT-4.5 | 70.4 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-ai2d-moon-phase-and-equinox · How the rankings work · Data refreshed daily, snapshot 2026-07-22.