#		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	73.5%	$1.38	54
2		Gemini 3.1 Pro Google	61.8%	$0.74	53
3		Claude Sonnet 4.6 Anthropic	60.5%	$10.26	279
4		Gemini 3 Flash Google	56.9%	$0.21	49
5		Claude Haiku 4.5 Anthropic	53.5%	$0.43	76
6		GPT 5 mini OpenAI	51.7%	$0.04	12
7		GPT 5.4 mini OpenAI	39.2%	$0.03	12
8		GPT 5.4 OpenAI	8.8%	$0.21	14
9		Claude Opus 4.6 Anthropic	0.0%	$1.32	185

Click row to see model details