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

Factuality Evaluation on AITutor-EvalKit (test)

96.2Overall Score

GPT-5

Updated 1mo ago

Evaluation Results

Method	Links
GPT-5 2026.06		96.2	97.49	95.01
GPT-4.1-nano + SFT V4 2026.06		84.4	75.57	92.51
Qwen3-8B + DPO V4* 2026.06		70.1	56.99	82.15
GPT-4.1-nano + DPO V4 2026.06		66.7	70.56	63.15
Qwen3-8B + DPO V4 2026.06		60.1	42.59	76.2
Qwen3-8B + SFT V4 2026.06		59.7	39.67	78.12
Qwen3-4B + DPO V2 2026.06		58.3	39.04	76.01
Qwen3-4B + SFT V2 2026.06		56.1	35.85	74.57
Qwen3-4B + DPO V4 2026.06		56	35.91	74.47
Qwen3-4B + SFT V4 2026.06		55.7	33.82	75.82
Qwen3-8B + SFT V2 2026.06		55.6	35.91	73.7
Qwen3-4B + DPO V3 2026.06		53.2	40.08	65.26
Qwen3-8B + DPO V3 2026.06		51.5	38.83	63.15
SocraticLM 2026.06		50.2	51.17	49.34
Qwen3-8B + SFT V3 2026.06		49.7	26.51	71.02
Qwen3-4B + SFT V3 2026.06		48.6	27.97	67.56
Qwen3-8B + DPO V1 2026.06		48.4	42.17	54.13
Qwen3-8B + SFT V1 2026.06		46.3	21.5	69.1
Qwen3-4B + SFT V1 2026.06		43.1	24.01	60.65
TutorRL-7B 2026.06		39.8	33.4	45.68
Qwen3-8B + DPO V2 2026.06		39.2	28.39	49.14
GPT-4.1-nano 2026.06		38.1	15.87	58.54
Qwen3-4B + DPO V1 2026.06		32.9	24.63	40.5
Qwen3-8B 2026.06		13.7	2.09	24.38
Qwen3-4B 2026.06		11.7	3.13	19.58