#		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	74.3%	$1.65	70
2		Claude Opus 4.6 Anthropic	58.9%	$15.76	297
3		Claude Sonnet 4.6 Anthropic	48.3%	$23.52	407
4		Claude Haiku 4.5 Anthropic	44.0%	$0.88	175
5		GPT 5.4 OpenAI	30.2%	$0.24	13
6		Gemini 3 Flash Google	26.2%	$0.16	35
7		GPT 5.4 mini OpenAI	26.0%	$0.02	7
8		Gemini 3.1 Pro Google	22.6%	$1.63	80
9		GPT 5 mini OpenAI	22.3%	$0.02	16

Click row to see model details