#		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	77.5%	$18.00	279
2		Claude Opus 4.7 Anthropic	72.2%	$8.06	134
3		Claude Sonnet 4.6 Anthropic	67.0%	$44.94	645
4		GPT 5.4 OpenAI	42.8%	$0.52	16
5		Gemini 3.1 Pro Google	40.5%	$1.73	90
6		Claude Haiku 4.5 Anthropic	37.4%	$1.43	196
7		Gemini 3 Flash Google	30.3%	$0.28	68
8		GPT 5.4 mini OpenAI	9.1%	$0.03	10
9		GPT 5 mini OpenAI	2.3%	$0.03	17

Click row to see model details