LLM Evaluation on Curated Population (MATH-500, MMLU-Redux, SimpleQA) benchmark leaderboard · SOTA2 Research

LLM Evaluation on Curated Population (MATH-500, MMLU-Redux, SimpleQA)

82.57Accuracygemini-2.5-pro

Evaluation Results

Method	Links
gemini-2.5-pro2026.02		82.57	68.51	76.69	90.07	71.23	84.37	79.08	72.75	62.51	86.91	95.34
grok-4-07092026.02		81.92	68.7	79.48	89.29	71.62	83.39	77.55	72.54	66.89	84.89	95.2
gpt-5-2025-08-072026.02		81.51	68.52	79.19	89.05	71.79	83.22	77.04	72.46	66.28	84.49	95.32
o3-2025-04-162026.02		81.14	67.7	78.4	88.81	70.58	83.04	77.06	72.02	64.8	84.79	95.16
grok-32026.02		76.69	59.63	70.05	83.78	65.51	78	73.58	64.31	59.25	79.61	91.65
o3-mini-2025-01-312026.02		67.39	49.95	56.67	69.83	60.86	65.62	67	52.33	51.41	67.91	73.96
gpt-5-nano-2025-08-072026.02		66.81	51.42	58.43	68.6	61.61	64.59	66.5	52.59	55.37	67.17	71.8
claude-3-5-sonnet-202410222026.02		66.08	43.66	53.21	71.73	54.42	65.86	66.67	47.88	42.7	70.54	80.82
doubao-seed-1-6-2506152026.02		65.01	44.42	50.47	68.17	55.86	63.69	66.17	46.83	42.8	67.72	75.19
doubao-seed-1-6-flash-2507152026.02		64.45	48.32	51.62	65.43	58.13	62.09	65.77	50.34	47.76	65.98	67.09
MiniMax-Text-012026.02		48.85	25.98	41.34	49.4	47.23	42.09	45.72	26.11	40.77	44.52	51.87
qwen3-30b-a3b2026.02		46.62	23.44	29.14	45.4	45.4	38.53	48.58	23.42	35.19	46.76	42.06
qwen3-32b2026.02		43.8	20.61	28.78	41.59	42.97	35.8	44.66	20.32	33.34	41.66	38.85
glm-4.5-air2026.02		43.64	18.3	31.57	42.37	43.6	34.25	42.77	17.82	36.61	40.36	40.94
gpt-4.1-nano-2025-04-142026.02		38.79	17.25	26.77	36.67	39.48	29.95	39.21	17.57	33.67	36.62	32.45