#		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 mini OpenAI	20.0%	$0.02	14
2		GPT 5.4 OpenAI	16.3%	$0.23	8
3		Gemini 3 Flash Google	12.6%	$0.24	114
4		Claude Opus 4.7 Anthropic	10.1%	$0.56	25
5		Gemini 3.1 Pro Google	8.6%	$1.18	94
6		Claude Haiku 4.5 Anthropic	8.3%	$0.60	104
7		GPT 5.4 mini OpenAI	7.1%	$0.02	9
8		Claude Sonnet 4.6 Anthropic	4.0%	$31.22	581
9		Claude Opus 4.6 Anthropic	0.0%	$1.93	213

Click row to see model details