#		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		Gemini 3.1 Pro Google	33.2%	$1.72	109
2		Gemini 3 Flash Google	33.1%	$0.24	83
3		Claude Opus 4.7 Anthropic	31.8%	$1.16	48
4		GPT 5 mini OpenAI	28.1%	$0.02	11
5		Claude Haiku 4.5 Anthropic	28.0%	$0.62	129
6		Claude Sonnet 4.6 Anthropic	24.2%	$21.25	514
7		GPT 5.4 OpenAI	13.4%	$0.26	9
8		GPT 5.4 mini OpenAI	3.1%	$0.03	8
9		Claude Opus 4.6 Anthropic	0.0%	$2.85	253

Click row to see model details