Fact-checking on InFi-Check-FG 1.0 (test) benchmark leaderboard · SOTA2 Research

Fact-checking on InFi-Check-FG 1.0 (test)

18.82PredELlama-3.1-8B-Instruct

Evaluation Results

Method	Links
Llama-3.1-8B-Instruct2026.01		18.82	9.52	31.03	3.13	0	0	61.11	17.66
Llama-3.1-8B-Instruct2026.01		32.94	4.76	13.79	26.56	0	0	88.49	23.79
GPT-52026.01		63.53	57.14	62.07	42.19	16.67	60.53	41.27	49.06
GPT-52026.01		63.53	61.9	51.72	45.31	13.33	47.37	41.27	46.35
Claude-3.7-Sonnet2026.01		68.24	71.43	34.48	21.88	23.33	78.95	46.03	49.19
Claude-3.7-Sonnet2026.01		70.59	66.67	34.48	37.5	26.67	81.58	53.97	53.07
DeepSeek-V3.2-NoThink2026.01		75.29	71.43	55.17	15.62	13.33	89.47	94.05	59.19
Qwen3-8B2026.01		76.47	52.38	44.83	50	0	50	61.9	47.94
Qwen3-8B2026.01		76.47	52.38	24.14	70.31	0	50	80.16	50.49
DeepSeek-V3.2-NoThink2026.01		78.82	76.19	58.62	9.38	26.67	86.84	80.95	59.64
GPT-4o2026.01		80	76.19	44.83	50	3.33	84.21	84.92	60.5
o32026.01		80	61.9	58.62	43.75	0	81.58	80.16	58
o32026.01		81.18	57.14	58.62	56.25	3.33	81.58	87.3	60.77
GPT-4o2026.01		84.71	61.9	44.83	75	0	94.74	91.67	64.69
GPT-4.12026.01		85.88	76.19	37.93	42.19	0	63.16	75.79	54.45
GPT-4.12026.01		85.88	76.19	41.38	56.25	3.33	68.42	80.95	58.91
InFi-Checker-Qwen2026.01		93.51	91.67	87.5	100	88.89	96.77	88.01	92.34
InFi-Checker-Llama2026.01		95.29	90.48	79.31	95.31	86.67	100	89.29	90.91