Metric: Accuracy (Top-1) (higher is better)
| # | Model↕ | Accuracy (Top-1)▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | Oyrx (34B) | 71.4 | No | Oryx MLLM: On-Demand Spatial-Temporal Understand... | 2024-09-19 | Code |
| 2 | BIMBA-LLaVA-Qwen2-7B | 68.51 | No | BIMBA: Selective-Scan Compression for Long-Range... | 2025-03-12 | Code |
| 3 | InternVideo2 (8B) | 63.4 | No | InternVideo2: Scaling Foundation Models for Mult... | 2024-03-22 | Code |
| 4 | VideoLLaMA2 (72B) | 57.5 | No | VideoLLaMA 2: Advancing Spatial-Temporal Modelin... | 2024-06-11 | Code |
| 5 | TraveLER | 50.2 | No | TraveLER: A Modular Multi-LMM Agent Framework fo... | 2024-04-01 | Code |
| 6 | Flamingo | 0.46 | No | Perception Test: A Diagnostic Benchmark for Mult... | 2023-05-23 | Code |