#		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	93.9%	$13.55	325
2		Claude Opus 4.7 Anthropic	92.3%	$3.11	108
3		Claude Sonnet 4.6 Anthropic	88.0%	$22.96	627
4		Gemini 3.1 Pro Google	87.6%	$1.46	104
5		Gemini 3 Flash Google	84.4%	$0.29	140
6		Claude Haiku 4.5 Anthropic	78.0%	$0.58	144
7		GPT 5.4 OpenAI	60.8%	$0.30	14
8		GPT 5.4 mini OpenAI	37.8%	$0.03	9
9		GPT 5 mini OpenAI	1.2%	$0.02	13

Click row to see model details