MM-Vet
Harbor: pendingMM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities
- Samples
- N/A
- Released
- 2023
- Scores
- 43
Benchmarking Multimodal Large Language Models for Zero-Shot Human-Object Interaction
A benchmark framework evaluating MLLMs on zero-shot Human-Object Interaction recognition and detection using adapted HICO, HICO-DET, and V-COCO datasets with novel QA annotations.
$ npm i -g lettokenburn-cli$ ltb bench info mllms-zs-hoi
External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
| Harness | Source | Confidence | Link | |||
|---|---|---|---|---|---|---|
| Qwen2-VL-7B | 52.9 | N/A | Independent | medium | Oct 13, 2026 | arxiv.org |
| Qwen2-VL-2B | 51.4 | N/A | Independent | medium | Oct 13, 2026 | arxiv.org |
| MiniCPM-V 1 | 48.2 | N/A | Independent | medium | Oct 13, 2026 | arxiv.org |
| MiniCPM-V 2 | 47.5 | N/A | Independent | medium | Oct 13, 2026 | arxiv.org |
| LLaVA-OV-0.5B | 46.1 | N/A | Independent | medium | Oct 13, 2026 | arxiv.org |
| InternVL2.5-2B | 43.5 | N/A | Independent | medium | Oct 13, 2026 | arxiv.org |
| InternVL2.5-1B | 41.8 | N/A | Independent | medium | Oct 13, 2026 | arxiv.org |
| Phi-3.5-Vision | 40.4 | N/A | Independent | medium | Oct 13, 2026 | arxiv.org |
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
The benchmark transforms standard HOI datasets (HICO, HICO-DET, V-COCO) into question-answer formats with new annotations. It introduces a taxonomy of zero-shot prompting strategies and visual prompting methods like Objects as Context.
Scoring converts token-level logits into interaction scores to enable mAP calculation. Experiments show state-of-the-art zero-shot performance, achieving 53.50 mAP on HICO and 23.69 mAP on HICO-DET.