#		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 Haiku 4.5 Anthropic	14.6%	$0.74	112
2		GPT 5 mini OpenAI	13.8%	$0.04	15
3		Claude Opus 4.6 Anthropic	10.6%	$6.95	175
4		Gemini 3 Flash Google	8.8%	$0.20	74
5		Gemini 3.1 Pro Google	4.6%	$1.64	94
6		Claude Sonnet 4.6 Anthropic	3.1%	$15.02	370
7		Claude Opus 4.7 Anthropic	2.8%	$0.62	27
8		GPT 5.4 OpenAI	2.4%	$0.24	9
9		GPT 5.4 mini OpenAI	1.9%	$0.03	11

Click row to see model details