#		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 4.7 Anthropic	96.6%	$3.36	104
2		Claude Opus 4.6 Anthropic	94.0%	$6.93	165
3		Claude Sonnet 4.6 Anthropic	92.2%	$3.78	175
4		Claude Haiku 4.5 Anthropic	74.2%	$0.48	87
5		GPT 5 mini OpenAI	66.3%	$0.02	18
6		GPT 5.4 OpenAI	62.1%	$0.22	10
7		Gemini 3 Flash Google	59.3%	$0.30	59
8		GPT 5.4 mini OpenAI	18.3%	$0.01	9
9		Gemini 3.1 Pro Google	0.0%	$1.11	48

Click row to see model details