#		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		Gemini 3.1 Pro Google	83.9%	$1.02	72
2		Claude Opus 4.7 Anthropic	83.6%	$0.84	44
3		Claude Haiku 4.5 Anthropic	82.9%	$0.22	80
4		Claude Opus 4.6 Anthropic	79.6%	$10.78	281
5		GPT 5 mini OpenAI	76.9%	$0.01	12
6		Gemini 3 Flash Google	71.2%	$0.19	54
7		GPT 5.4 mini OpenAI	39.0%	$0.03	8
8		GPT 5.4 OpenAI	38.1%	$0.12	7
9		Claude Sonnet 4.6 Anthropic	0.0%	$14.93	382

Click row to see model details