Image-to-image matching on Factify-V (test)
80.6AccuracyGPT-4V + CoCoT
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4V + CoCoTprompting_strategy=CoCoT, zero-shot=true, web_version_as_of=December 30, 20232024.01 | 80.6 | |
| GEMINI + CCoTprompting_strategy=CCoT, zero-shot=true, temperature=0.4, TopK=32, TopP=1, max_length=40962024.01 | 80.2 | |
| GEMINI + CoCoTprompting_strategy=CoCoT, zero-shot=true, temperature=0.4, TopK=32, TopP=1, max_length=40962024.01 | 77.8 | |
| MMICL + CoCoTprompting_strategy=CoCoT, zero-shot=true, beam_search_width=82024.01 | 77 | |
| GPT-4Vprompting_strategy=standard, zero-shot=true, web_version_as_of=December 30, 20232024.01 | 74 | |
| MMICL + CCoTprompting_strategy=CCoT, zero-shot=true, beam_search_width=82024.01 | 73.2 | |
| MMICL + DDCoTprompting_strategy=DDCoT, zero-shot=true, beam_search_width=82024.01 | 68.4 | |
| GEMINI + DDCoTprompting_strategy=DDCoT, zero-shot=true, temperature=0.4, TopK=32, TopP=1, max_length=40962024.01 | 65.4 | |
| OPENFLAMINGO + CoCoTprompting_strategy=CoCoT, zero-shot=true, beam_search_width=32024.01 | 65 | |
| MMICLprompting_strategy=standard, zero-shot=true, beam_search_width=82024.01 | 64.6 | |
| OPENFLAMINGO + CCoTprompting_strategy=CCoT, zero-shot=true, beam_search_width=32024.01 | 63.2 | |
| OPENFLAMINGO + DDCoTprompting_strategy=DDCoT, zero-shot=true, beam_search_width=32024.01 | 58.4 | |
| GEMINIprompting_strategy=standard, zero-shot=true, temperature=0.4, TopK=32, TopP=1, max_length=40962024.01 | 58 | |
| OPENFLAMINGOprompting_strategy=standard, zero-shot=true, beam_search_width=32024.01 | 54 | |
| Random Choiceevaluation_type=baseline2024.01 | 50 |