#		Model	Score help_outline Percentage of hidden behavioral tests passed.	Cost help_outline Total API cost in USD for this task instance.	Calls help_outline Number of LLM API calls for this task instance.
1		Claude Opus 4.6 Anthropic	62.0%	$14.72	312
2		Claude Sonnet 4.6 Anthropic	57.6%	$20.85	417
3		GPT 5.4 OpenAI	32.9%	$0.22	8
4		Claude Opus 4.7 Anthropic	32.2%	$2.28	84
5		Gemini 3.1 Pro Google	27.1%	$3.32	161
6		Claude Haiku 4.5 Anthropic	19.3%	$1.04	133
7		GPT 5.4 mini OpenAI	12.0%	$0.05	31
8		GPT 5 mini OpenAI	10.1%	$0.03	19
9		Gemini 3 Flash Google	6.8%	$0.73	127

Click row to see model details