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

Mathematical Reasoning on AIME24 (Accuracy, Performance Gain %)

75Accuracy

Qwen3-32B

Updated 1mo ago

Evaluation Results

Method	Links
Qwen3-32B 2026.06		75	5.81
Qwen3-14B 2026.06		73.33	11.43
Qwen3-8B 2026.06		71.66	12.57
Qwen3-32B 2026.06		70.83	-
Qwen3-4B 2026.06		70	16.67
LLaMA-70B 2026.06		66.67	5.25
Qwen3-14B 2026.06		65.83	-
Qwen3-8B 2026.06		63.67	-
LLaMA-70B 2026.06		63.33	-
Qwen3-4B 2026.06		60	-
Qwen3-1.7B 2026.06		48.33	20.83
LLaMA-8B 2026.06		47.5	18.75
Qwen3-1.7B 2026.06		40	-
LLaMA-8B 2026.06		40	-