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

Scientific Claim Verification on SCIFACT abstract-level (test)

89.9Support F1

Qwen-7B

Updated 1mo ago

Evaluation Results

Method	Links
Qwen-7B 2026.06		89.9	82.5	90.61	87.37
Qwen-Max 2026.06		89.55	85.62	79.65	84.94
DeepSeek-V3 2026.06		89.17	84.71	79.25	84.38
Qwen-Max 2026.06		87.57	82.42	80.19	83.39
DeepSeek-R1 2026.06		87.14	82.22	72.81	80.72
Qwen-plus 2026.06		85.92	79.04	72.51	79.16
DeepSeek-V3 2026.06		85.33	80.05	78.78	81.39
Qwen-plus 2026.06		82.84	79.66	63.97	75.49
DeepSeek-R1-Distill-Llama-8B 2026.06		78.81	67.32	84.23	76.79
DeepSeek-R1-Distill-Llama-8B 2026.06		77.56	73.83	56.82	69.4
DeepSeek-R1 2026.06		65.88	39.37	32.63	45.96
Qwen-7B 2026.06		63.24	9.08	34.55	35.62