#		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 Sonnet 4.6 Anthropic	90.7%	$19.93	394
2		Claude Opus 4.7 Anthropic	84.6%	$5.68	110
3		Claude Opus 4.6 Anthropic	80.3%	$10.59	262
4		Gemini 3.1 Pro Google	52.8%	$1.03	69
5		Gemini 3 Flash Google	46.7%	$0.34	100
6		GPT 5 mini OpenAI	1.6%	$0.02	14
7		GPT 5.4 OpenAI	0.9%	$0.52	18
8		Claude Haiku 4.5 Anthropic	0.9%	$0.63	122
9		GPT 5.4 mini OpenAI	0.7%	$0.05	11

Click row to see model details