Our new X account is live! Follow @wizwand_team for updates

Target Generation on VAST Non-explicit (test)

0.9SemSim Score (SS)

TSE-M

Updated 4d ago

Evaluation Results

Method	Links
TSE-M 2024.08		0.9	30.56	0.391
Llama-3-8B 2024.08		0.85	33.06	0.447
Llama-3-70B 2024.08		0.85	34.67	0.488
Mistral-large 2024.08		0.85	35.38	0.465
GPT-3.5 2024.08		0.84	33.1	0.419
GPT-4o 2024.08		0.84	35.14	0.43
Gemini-flash 2024.08		0.84	34.59	0.347
Gemini-pro 2024.08		0.84	34.85	0.453
Llama-3-70B 2024.08		0.84	32.98	0.48
GPT-3.5 2024.08		0.83	31.32	0.405
GPT-4o 2024.08		0.83	36.12	0.513
Gemini-flash 2024.08		0.83	34.73	0.365
Gemini-pro 2024.08		0.83	33.44	0.365
Llama-3-8B 2024.08		0.83	33.81	0.49
Mistral-small 2024.08		0.83	30.18	0.386
Mistral-small 2024.08		0.83	34.12	0.495
Mistral-large 2024.08		0.83	35.42	0.488
TSE-B 2024.08		0.82	29.32	0.215