#		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	85.5%	$9.59	142
2		Claude Sonnet 4.6 Anthropic	81.4%	$12.78	294
3		Gemini 3.1 Pro Google	70.1%	$1.71	81
4		Gemini 3 Flash Google	57.5%	$0.27	57
5		Claude Haiku 4.5 Anthropic	44.9%	$1.23	122
6		GPT 5.4 OpenAI	44.5%	$0.40	9
7		GPT 5 mini OpenAI	23.1%	$0.05	8
8		GPT 5.4 mini OpenAI	2.0%	$0.05	29
9		Claude Opus 4.6 Anthropic	0.0%	$3.29	258

Click row to see model details