Legal Reasoning on LexEval

74.9MemoizationDoubao-Seed-2.0-Pro

Evaluation results

Method
Doubao-Seed-2.0-Pro2026.04	74.9	88.51	81.62	30.07	20.2	72.97	65.95
GLM-52026.04	66.76	90.69	80.62	37.53	25.73	60.9	65.14
Qwen3.5-397B-A17B2026.04	65.2	90.64	80.72	38.9	24.15	64.63	65.28
Kimi-K2.52026.04	64.89	85.25	76.48	38.5	21.27	68.77	62.96
Doubao-Seed-2.0-mini2026.04	64.86	86	73.68	28.67	19.39	67.57	61.05
Kimi-K2-thinking2026.01	63.78	88.75	76.41	42.9	72.38	68.6	72.81
LegalOne-8B2026.01	62.68	87.77	74.66	41.63	68.95	67.83	71.19
GPT-52026.01	62.31	85.69	73.59	41.07	72.88	73.43	71.78
PoliLegalLM-30B-A3B2026.04	60.39	82.84	76.38	38.17	27.09	63.67	62.15
PoliLegalLM-30B-A3B2026.04	60.39	82.84	76.38	38.17	27.09	63.67	62.15
GPT-52026.04	60.2	84.33	74.46	40.73	20.55	69.73	61.82
LegalOne-4B2026.01	58.59	86.63	72.62	36.87	63.48	60.77	67.59
Qwen3-Max2026.01	58.46	88	75.82	33	66.88	59.7	68.82
Qwen3-235B-A22B2026.01	58.32	85.61	73.24	37.47	73.5	62.17	69.47
Qwen3-235B-A22B2026.04	56.97	86.68	71.82	39	20.91	60.13	59.88
GLM-4.72026.01	56.5	88.31	72.86	33.7	69.18	61.03	68.49
DeepSeek-v3.22026.01	55.4	86.67	73.19	29.6	70.2	63.37	68.21
Qwen3.5-35B-A3B2026.04	52.71	86.28	68.06	32.83	20.45	55.67	57.06
Qwen3-30B-A3B2026.04	51.73	85.57	63.74	28.3	18.99	55.8	55.02
DeepSeek-V3.22026.04	51.34	85.69	72.13	32.33	23.76	54.53	58.2
LegalOne-1.7B2026.01	50.96	82.55	65.63	30.63	55.63	49.93	60.56
DeepSeek-R12026.01	49.64	86.91	74.07	33.8	68.88	64.77	68.05
Qwen3-8B2026.01	49.62	79.31	60.16	29.77	60.65	57.6	60.06
Grok-4.22026.04	47.02	87.45	65.77	35.4	21.37	43.77	54.81
PoliLegalLM-32B2026.04	44.86	87.67	66.39	29.17	28.68	47.3	55.92
PoliLegalLM-32B2026.04	44.86	87.67	66.39	29.17	28.68	47.3	55.92
Qwen3-4B2026.01	44.26	78.49	54.74	23.54	59.15	55.63	56.71
GLM-4.7-FlashX2026.04	42.49	81.89	54.41	27.3	23.09	43.13	49.55
GPT-5-Mini2026.04	39.93	84.36	66.43	40.83	14.78	64.63	55.43
GPT-4o2026.01	39.74	84.12	65.77	33.97	63.93	58.47	62.32
Grok-4.1-Fast2026.04	32.81	83.4	61.16	32.73	20.17	52.73	51.6
Qwen3-1.7B2026.01	29.66	64.29	54.93	24.34	51.5	48.23	49.54
GPT-4o-mini2026.01	24.19	83.59	50.23	30.9	59.03	42.4	52.91
ChatLaw-33B2026.04	16.31	57.87	32.18	13.55	15.55	22.87	29.97
WisdomInterrogatory2026.04	3.2	4.49	1.83	10.54	20.59	4.53	6.96