#		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	90.7%	$7.87	169
2		Claude Sonnet 4.6 Anthropic	81.0%	$19.64	522
3		Claude Opus 4.6 Anthropic	80.9%	$13.21	319
4		Gemini 3.1 Pro Google	78.0%	$1.41	121
5		GPT 5.4 OpenAI	65.4%	$0.25	10
6		GPT 5.4 mini OpenAI	46.7%	$0.05	14
7		Claude Haiku 4.5 Anthropic	31.9%	$0.74	156
8		Gemini 3 Flash Google	21.2%	$0.29	128
9		GPT 5 mini OpenAI	15.9%	$0.02	24

Click row to see model details