Share your thoughts, 1 month free Claude Pro on usSee more

Target Generation on EZSTANCE Non-explicit (test)

0.85SS (SemSim)

GPT-3.5

Updated 1mo ago

Evaluation Results

Method	Links
GPT-3.5 2024.08		0.85	38.55	0.416
Llama-3-8B 2024.08		0.84	39.91	0.383
Llama-3-70B 2024.08		0.84	42.02	0.451
Mistral-large 2024.08		0.84	39.98	0.424
GPT-4o 2024.08		0.83	39.84	0.45
Gemini-flash 2024.08		0.83	39.27	0.394
Llama-3-70B 2024.08		0.83	40.47	0.447
Gemini-pro 2024.08		0.82	40.53	0.482
Llama-3-8B 2024.08		0.82	38.74	0.33
Mistral-large 2024.08		0.82	39.32	0.394
Gemini-flash 2024.08		0.81	39.22	0.306
Mistral-small 2024.08		0.81	40.05	0.447
GPT-4o 2024.08		0.8	38.55	0.387
Gemini-pro 2024.08		0.8	39.9	0.447
Mistral-small 2024.08		0.8	39.75	0.405
GPT-3.5 2024.08		0.79	38.1	0.31