OpenVLM Video - MMBench-Video - Temporal Reasoning: leaderboard
Metric: GPT-4 Rating (0-3). Source: huggingface.co. 45 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o (2024-08-06) | 1.97 |
| 2 | InternVL2.5-78B | 1.77 |
| 3 | Gemini 2.0 Flash | 1.67 |
| 4 | Gemini 1.5 Pro | 1.63 |
| 5 | Qwen 2 VL 72B | 1.52 |
| 6 | InternVL3-78B | 1.49 |
| 7 | InternVL3-8B | 1.43 |
| 8 | Gemini 1.5 Flash | 1.39 |
| 9 | Qwen 2 VL 7B | 1.21 |
| 10 | Claude 3.5 Sonnet | 1.04 |
| 11 | InternVL2-8B | 1 |
| 12 | Phi-4 Multimodal Instruct | 0.7 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-video-mmbench-video-temporal-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-19.