#		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 4.7 Anthropic	90.2%	$9.93	206
2		Claude Opus 4.6 Anthropic	87.9%	$15.33	358
3		Claude Sonnet 4.6 Anthropic	84.4%	$14.17	459
4		Gemini 3 Flash Google	79.0%	$0.31	121
5		Gemini 3.1 Pro Google	71.0%	$1.56	177
6		Claude Haiku 4.5 Anthropic	70.5%	$0.69	107
7		GPT 5.4 OpenAI	58.0%	$0.36	13
8		GPT 5 mini OpenAI	22.3%	$0.03	11
9		GPT 5.4 mini OpenAI	20.1%	$0.03	10

Click row to see model details