OpenVLM AI2D - Life Cycles — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 284 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 90.6 |
| 2 | InternVL3-78B | 89.4 |
| 3 | GPT-5 (2025-08-07) | 89.2 |
| 4 | InternVL3-38B | 89 |
| 5 | GPT-4o ChatGPT | 87.5 |
| 6 | GPT-4.5 | 87.3 |
| 7 | GPT-5 Mini (2025-08-07) | 87.3 |
| 8 | Qwen 2 VL 72B | 86.8 |
| 9 | GPT-4.1 (2025-04-14) | 86.8 |
| 10 | InternVL2.5-78B | 86.1 |
| 11 | Ovis2-8B | 85.9 |
| 12 | InternVL3-8B | 84.2 |
| 13 | InternVL3-14B | 83.7 |
| 14 | Gemini 2.0 Flash | 83.7 |
| 15 | Gemini 1.5 Flash (002) | 83.2 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-ai2d-life-cycles · How the rankings work · Data refreshed daily, snapshot 2026-07-22.