InstructBLIP-7B

Reported on 3 benchmarks across 3 tasks · 1 paper · 1 SOTA

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

Natural Language Processing3 results

Instruction FollowingonLLaVA-Bench
avg score· 2023-05-11
60.9
best: 85.7 (CuMo-7B)
SOTA
InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning arXiv:2305.06500
Visual Question Answering (VQA)onBenchLMM
GPT-3.5 score· 2023-05-11
44.63
best: 58.37 (GPT-4V)
InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning arXiv:2305.06500
Visual Question AnsweringonBenchLMM
GPT-3.5 score· 2023-05-11
44.63
best: 58.37 (GPT-4V)
InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning arXiv:2305.06500