LLaVA-NeXT-Inst-IT-Qwen2-7B (Visual Prompt

Reported on 4 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing4 results

Visual Question Answering (VQA)onViP-Bench
GPT-4 score (bbox)· uses extra data· 2024-12-04
50.5
best: 60.7 (GPT-4V-turbo-detail:high (Visual Prompt))
Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning arXiv:2412.03565
Visual Question Answering (VQA)onViP-Bench
GPT-4 score (human)· uses extra data· 2024-12-04
49
best: 59.9 (GPT-4V-turbo-detail:high (Visual Prompt))
Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning arXiv:2412.03565
Visual Question AnsweringonViP-Bench
GPT-4 score (bbox)· uses extra data· 2024-12-04
50.5
best: 60.7 (GPT-4V-turbo-detail:high (Visual Prompt))
Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning arXiv:2412.03565
Visual Question AnsweringonViP-Bench
GPT-4 score (human)· uses extra data· 2024-12-04
49
best: 59.9 (GPT-4V-turbo-detail:high (Visual Prompt))
Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning arXiv:2412.03565