deep Planning

6 models evaluated

#	Model	Provider	Type	Score
1	Qwen3.6 Plus	Alibaba	Closed	41.5%
2	Qwen3.5 397B	Alibaba	Open	37.6%
3	Claude Opus 4.5	Anthropic	Closed	26.4%
4	Qwen3.6-35B-A3B	Alibaba	Open	25.9%
5	GLM-5	Z.AI	Open	14.6%
6	Kimi K2.5	Moonshot AI	Open	14.4%