#		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	94.6%	$8.74	301
2		Gemini 3.1 Pro Google	81.7%	$1.66	176
3		Claude Opus 4.7 Anthropic	79.3%	$5.22	143
4		Claude Haiku 4.5 Anthropic	54.9%	$0.94	145
5		GPT 5.4 OpenAI	52.0%	$0.24	12
6		Gemini 3 Flash Google	52.0%	$0.51	142
7		Claude Sonnet 4.6 Anthropic	45.8%	$7.56	370
8		GPT 5 mini OpenAI	24.2%	$0.02	15
9		GPT 5.4 mini OpenAI	11.0%	$0.04	8

Click row to see model details