#		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 Sonnet 4.6 Anthropic	75.8%	$58.91	840
2		Claude Opus 4.7 Anthropic	75.6%	$2.18	65
3		Claude Opus 4.6 Anthropic	72.0%	$20.30	324
4		GPT 5.4 mini OpenAI	62.9%	$0.10	10
5		GPT 5.4 OpenAI	59.7%	$0.26	8
6		Gemini 3 Flash Google	56.6%	$0.67	130
7		GPT 5 mini OpenAI	26.2%	$0.02	13
8		Gemini 3.1 Pro Google	2.1%	$1.56	51
9		Claude Haiku 4.5 Anthropic	0.0%	$0.87	101

Click row to see model details