#		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		GPT 5.4 OpenAI	89.9%	$0.15	140
2		Claude Opus 4.7 Anthropic	63.9%	$2.69	80
3		Claude Haiku 4.5 Anthropic	33.4%	$0.92	111
4		Gemini 3 Flash Google	18.7%	$0.21	46
5		Gemini 3.1 Pro Google	16.1%	$0.72	60
6		GPT 5 mini OpenAI	7.8%	$0.01	10
7		Claude Opus 4.6 Anthropic	1.1%	$18.26	384
8		Claude Sonnet 4.6 Anthropic	1.0%	$4.40	289
9		GPT 5.4 mini OpenAI	1.0%	$0.02	15

Click row to see model details