Video Understanding on Perception (test)
82.7AccuracyPLM-8B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PLM-8BAccess Type=Open models2026.01 | 82.7 | — | |
| Molmo2-8BAccess Type=Molmo2 family2026.01 | 82.1 | — | |
| Molmo2-4BAccess Type=Molmo2 family2026.01 | 81.3 | — | |
| Eagle2.5-8BAccess Type=Open weights only2026.01 | 81 | — | |
| Molmo2-O-7BAccess Type=Molmo2 family2026.01 | 79.6 | — | |
| GPT-5Access Type=API call only2026.01 | 79.4 | — | |
| PLM-3BAccess Type=Open models2026.01 | 79.3 | — | |
| Gemini 2.5 ProAccess Type=API call only2026.01 | 78.4 | — | |
| Gemini 3 ProAccess Type=API call only2026.01 | 77.6 | — | |
| VideoChat-Flash-7BAccess Type=Open models2026.01 | 76.5 | — | |
| Gemini 2.5 FlashAccess Type=API call only2026.01 | 74.7 | — | |
| GLM-4.1V-9BAccess Type=Open weights only2026.01 | 74.2 | — | |
| InternVL3.5-8BAccess Type=Open weights only2026.01 | 72.7 | — | |
| Qwen3-VL-8BAccess Type=Open weights only2026.01 | 72.7 | — | |
| GPT-5 miniAccess Type=API call only2026.01 | 72 | — | |
| MiniCPM-V-4.5-8BAccess Type=Open weights only2026.01 | 70.9 | — | |
| Qwen3-VL-4BAccess Type=Open weights only2026.01 | 70.7 | — | |
| LLaVA-Video-7BAccess Type=Open models2026.01 | 68.8 | — | |
| InternVL3.5-4BAccess Type=Open weights only2026.01 | 68.1 | — | |
| Qwen2-VL-72BParameters=72B2024.09 | 68 | — | |
| Previous SoTA2024.09 | 66.9 | — | |
| LLaVA-OV-72BBackbone=72B2024.12 | 66.9 | — | |
| Claude Sonnet 4.5Access Type=API call only2026.01 | 64.3 | — | |
| Keye-VL-1.5-8BAccess Type=Open weights only2026.01 | 64.2 | — | |
| Qwen2-VL-7BParameters=7B2024.09 | 62.3 | — | |
| LLaVA-OV-72Bvariant=Single-Image (SI), Backbone=72B2024.12 | 62.3 | — | |
| Qwen2-VL-7B-Ins.Backbone=7B-Instruct2024.12 | 62.3 | — | |
| Llama 3-V 70BZero-shot=true, Parameters=70B2024.07 | 60.8 | — | |
| MAmmoTH-VL-8BBackbone=8B2024.12 | 59.3 | — | |
| InternVL-2-8BBackbone=8B2024.12 | 57.4 | — | |
| LLaVA-OV-7BBackbone=7B2024.12 | 57.1 | — | |
| LLaVA-OV-7Bvariant=Single-Image (SI), Backbone=7B2024.12 | 54.9 | — | |
| Gemini 1.0 UltraZero-shot=true2024.07 | 54.7 | — | |
| Qwen2-VL-2BParameters=2B2024.09 | 53.9 | — | |
| Llama 3-V 8BZero-shot=true, Parameters=8B2024.07 | 53.8 | — | |
| Gemini 1.0 ProZero-shot=true2024.07 | 51.1 | — | |
| Video-LaVITZero-shot=true2024.02 | 47.9 | — | |
| VideoChat2Zero-shot=true2024.02 | 47.3 | — | |
| BLIP-2Zero-shot=true2024.02 | 39.2 | — | |
| FlamingoZero-shot=true2024.02 | 33.5 | — | |
| BaselineModel=Baseline, Pruning Strength=0%2026.03 | — | 78.7 | |
| CASA⊕ Q2.5VLMax Res.=448^22025.12 | — | 58.1 | |
| InternVL3.5-8BModel=InternVL3.5-8B, Pruning Strength=None2026.03 | — | 72.7 | |
| PLM-8BModel=PLM-8B, Pruning Strength=None2026.03 | — | 82.7 | |
| Qwen2.5VL 3BMax Res.=Native2025.12 | — | 67 | |
| Qwen3-VL-4BModel=Qwen3-VL-4B, Pruning Strength=None2026.03 | — | 70.7 | |
| STTSModel=STTS, Pruning Strength=30%2026.03 | — | 79 | |
| STTSModel=STTS, Pruning Strength=40%2026.03 | — | 77.3 | |
| STTSModel=STTS, Pruning Strength=50%2026.03 | — | 77.7 |