Auto71%Harbor: pendingMultimodalKnowledge & Reasoning

MM-Vet

MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

How to run

ltb · mm-vet
$ npm i -g lettokenburn-cli
$ ltb bench info mm-vet

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

Scores

43 sourced entries
HarnessSourceConfidenceLink
Gemini 2.0 Flash Experimental81.2N/AIndependentmediumN/Apaperswithcode.com
Gemini Exp 120678.1N/AIndependentmediumN/Apaperswithcode.com
Qwen2-VL-72B74.0N/AIndependentmediumSep 18, 2024arxiv.org
InternVL2.5-78B72.3N/AIndependentmediumDec 6, 2024arxiv.org
GLM-4V-Plus71.1N/AIndependentmediumAug 29, 2024arxiv.org
InternVL2.5-38B68.8N/AIndependentmediumDec 6, 2024arxiv.org
GPT-4o-mini68.6N/AIndependentmediumMar 15, 2023arxiv.org
GPT-4V67.7N/AIndependentmediumMar 15, 2023arxiv.org
GPT-4V-Turbo-detail:high67.6N/AIndependentmediumMar 15, 2023arxiv.org
Qwen-VL-Max66.6N/AIndependentmediumAug 24, 2023arxiv.org
Baichuan-Omni65.4N/AIndependentmediumOct 11, 2024arxiv.org
InternVL2.5-26B65.0N/AIndependentmediumDec 6, 2024arxiv.org
InternVL2-Llama3-76B64.4N/AIndependentmediumN/Apaperswithcode.com
GLM4 Vision63.9N/AIndependentmediumNov 6, 2023arxiv.org
LLaVA-OneVision-72B63.7N/AIndependentmediumAug 6, 2024arxiv.org
InternVL2.5-8B62.8N/AIndependentmediumDec 6, 2024arxiv.org
InternVL 1.562.8N/AIndependentmediumApr 25, 2024arxiv.org
MAmmoTH-VL-8B62.3N/AIndependentmediumDec 6, 2024arxiv.org
Qwen2-VL-7B62.0N/AIndependentmediumSep 18, 2024arxiv.org
InternVL2-40B61.8N/AIndependentmediumN/Apaperswithcode.com
Qwen-VL-Plus61.1N/AIndependentmediumAug 24, 2023arxiv.org
InternVL2.5-2B60.8N/AIndependentmediumDec 6, 2024arxiv.org
InternVL2.5-4B60.6N/AIndependentmediumDec 6, 2024arxiv.org
GLM-4V-9B58.0N/AIndependentmediumAug 29, 2024arxiv.org
LLaVA-OneVision-7B57.5N/AIndependentmediumAug 6, 2024arxiv.org
LLaVA-NeXT-34B57.4N/AIndependentmediumN/Apaperswithcode.com
InternLM-XComposer251.2N/AIndependentmediumJan 29, 2024arxiv.org
Qwen2-VL-2B49.5N/AIndependentmediumSep 18, 2024arxiv.org
InternVL 1.248.9N/AIndependentmediumApr 25, 2024arxiv.org
InternVL2.5-1B48.8N/AIndependentmediumDec 6, 2024arxiv.org
DeepSeek-VL41.5N/AIndependentmediumMar 8, 2024arxiv.org
LLaVA1.5-13B-MDA39.9N/AIndependentmediumNov 21, 2024arxiv.org
LLaVA-1.5-LLaMA3-8B37.8N/AIndependentmediumJun 12, 2024arxiv.org
LLaVA-COCO-13B37.5N/AIndependentmediumJan 17, 2024arxiv.org
LLaVA1.5-7B-BPO36.8N/AIndependentmediumMar 13, 2024arxiv.org
LLaVA-1.5-13B36.3N/AIndependentmediumOct 5, 2023arxiv.org
LLaVA-HR-X35.5N/AIndependentmediumMar 5, 2024arxiv.org
LLaVA1.5-7B-MDA35.2N/AIndependentmediumNov 21, 2024arxiv.org
LLaVA-1.5-7B31.1N/AIndependentmediumOct 5, 2023arxiv.org
LLaVA-AlignedVQ30.7N/AIndependentmediumNov 8, 2024arxiv.org
LLaVA-1.5-HACL30.4N/AIndependentmediumDec 12, 2023arxiv.org
LLaVA-OneVision-0.5B29.1N/AIndependentmediumAug 6, 2024arxiv.org
LLaVA-Phi28.9N/AIndependentmediumJan 4, 2024arxiv.org

Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.

Reproduced by the community

All runs
Loading community runs…

About

MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities