CHIMERA-4B-SFT

CHIMERA-4B-SFT is Qwen3-4B-Thinking-2507 fine-tuned on the CHIMERA dataset via supervised fine-tuning (SFT).

Results

SFT alone accounts for the majority of performance gains across benchmarks. See TianHongZXY/CHIMERA-4B-RL for the further RL-trained model.

Model	GPQA-D	AIME 24	AIME 25	AIME 26	HMMT Feb 25	HMMT Nov 25	HLE
Qwen3-4B-Thinking-2507	65.8	81.6	81.0	80.8	59.2	57.3	7.3
CHIMERA-4B-SFT	68.8	86.5	79.8	80.3	63.1	66.3	9.0
CHIMERA-4B-RL	70.1	86.9	80.7	82.7	65.7	67.0	9.0