#		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	78.5%	$10.87	211
2		Claude Opus 4.7 Anthropic	72.3%	$1.89	70
3		Claude Sonnet 4.6 Anthropic	58.7%	$11.38	271
4		GPT 5.4 OpenAI	49.6%	$0.18	8
5		Gemini 3.1 Pro Google	36.9%	$0.66	33
6		Gemini 3 Flash Google	29.8%	$0.22	64
7		GPT 5 mini OpenAI	21.8%	$0.01	7
8		GPT 5.4 mini OpenAI	20.9%	$0.03	18
9		Claude Haiku 4.5 Anthropic	16.2%	$0.48	113

Click row to see model details