#		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	13.4%	$10.16	341
2		Gemini 3 Flash Google	10.3%	$0.20	72
3		Claude Opus 4.7 Anthropic	8.8%	$1.07	43
4		GPT 5.4 OpenAI	7.9%	$0.23	9
5		Claude Haiku 4.5 Anthropic	7.2%	$0.92	121
6		Gemini 3.1 Pro Google	5.7%	$0.91	57
7		GPT 5.4 mini OpenAI	2.4%	$0.03	11
8		GPT 5 mini OpenAI	2.4%	$0.05	20
9		Claude Sonnet 4.6 Anthropic	0.0%	$3.96	395

Click row to see model details