#		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	84.2%	$11.72	273
2		Claude Opus 4.7 Anthropic	80.8%	$5.47	144
3		Claude Sonnet 4.6 Anthropic	76.5%	$7.18	249
4		Gemini 3.1 Pro Google	70.8%	$1.14	99
5		Gemini 3 Flash Google	69.0%	$0.30	94
6		Claude Haiku 4.5 Anthropic	51.7%	$0.74	112
7		GPT 5.4 OpenAI	28.8%	$0.17	7
8		GPT 5.4 mini OpenAI	17.8%	$0.03	7
9		GPT 5 mini OpenAI	10.2%	$0.02	17

Click row to see model details