Molmo2 Human Preference: leaderboard
Metric: Elo rating (bootstrap median, Bradley-Terry; pairwise human preferences on 450 video questions and 51 captioning videos). Source: arxiv.org. Saturation forecast: Around March 2027. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 1096 |
| 2 | Gemini 2.5 Flash | 1084 |
| 3 | Gemini 3 Pro | 1082 |
| 4 | GPT-5 Mini | 1076 |
| 5 | Molmo2-8B | 1057 |
| 6 | Qwen 3 VL 8B | 1054 |
| 7 | Qwen 3 VL 4B | 1048 |
| 8 | GPT-5 | 1031 |
| 9 | Claude Sonnet 4.5 | 1008 |
| 10 | GLM-4.1V-9B (Thinking) | 962 |
Interactive version: theaggregate.ai/benchmark?slug=molmo2-human-preference · How It Works · Data refreshed daily, snapshot 2026-09-25.