Target Generation on EZSTANCE Explicit (test) benchmark leaderboard · SOTA2 Research

Target Generation on EZSTANCE Explicit (test)

89SS (SemSim)GPT-3.5

Evaluation Results

Method	Links
GPT-3.52024.08		89	44.25	58.1
Mistral-large2024.08		89	43.13	67.1
GPT-4o2024.08		88	44.25	62.9
Gemini-flash2024.08		88	42.14	70.6
Llama-3-8B2024.08		88	42.45	45.8
Llama-3-70B2024.08		88	42.5	65.5
Gemini-pro2024.08		87	42.78	70.7
Llama-3-8B2024.08		86	41.13	46.7
Llama-3-70B2024.08		86	40.73	65.2
Mistral-small2024.08		86	43.71	52.6
Mistral-large2024.08		86	41.71	65.2
Gemini-flash2024.08		85	42.03	68.1
GPT-4o2024.08		84	42.69	51.9
Mistral-small2024.08		84	42.13	49
GPT-3.52024.08		83	41.67	46.1
Gemini-pro2024.08		83	42.52	68.6