	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	3rd 68.5%	2nd 68.8%	- -	1st 69.7%	5th 60.2%	4th 66.1%
55.6%	53%	43%		56%	53%	73%
47.4%	52%	52%		39%	53%	41%
56.0%	63%	55%		57%	57%	48%
56.8%	58%	54%		58%	57%	57%
68.4%	68%	75%		65%	66%	68%
65.2%	58%	67%		67%	67%	67%
78.4%	84%	85%		76%	77%	70%
60.2%	61%	57%		73%	61%	49%
71.6%	69%	80%		77%	65%	67%
71.4%	78%	80%		69%	61%	69%
64.0%	71%	76%		67%	47%	59%
63.4%	67%	63%		67%	57%	63%
66.2%	77%	83%		72%	36%	63%
59.0%	61%	54%		61%	59%	60%
58.6%	59%	47%		59%	66%	62%
79.8%	79%	84%		87%	65%	84%
66.0%	71%	64%		65%	66%	64%
74.8%	77%	71%		79%	76%	71%
55.2%	59%	58%		54%	54%	51%
63.6%	69%	75%		67%	41%	66%
55.6%	55%	61%		56%	54%	52%
72.0%	84%	59%		68%	63%	86%
88.8%	92%	86%		93%	86%	87%
66.0%	62%	76%		66%	63%	63%
60.8%	73%	78%		68%	30%	55%
61.6%	58%	65%		66%	54%	65%
70.4%	71%	60%		76%	71%	74%
62.0%	65%	61%		67%	54%	63%
87.6%	83%	85%		82%	94%	94%
68.8%	72%	70%		71%	65%	66%
57.8%	49%	60%		68%	50%	62%
71.8%	71%	72%		75%	71%	70%
72.4%	69%	71%		75%	70%	77%
66.2%	59%	82%		61%	61%	68%
76.6%	77%	86%		84%	59%	77%
72.8%	73%	74%		78%	68%	71%
70.2%	75%	74%		68%	65%	69%
67.8%	72%	81%		79%	50%	57%
53.2%	54%	59%		66%	34%	53%
73.6%	79%	71%		76%	71%	71%
72.4%	78%	69%		81%	59%	75%
77.2%	73%	72%		82%	78%	81%
56.0%	57%	67%		59%	51%	46%
62.4%	59%	63%		69%	51%	70%
81.2%	87%	75%		90%	65%	89%
59.8%	71%	65%		65%	49%	49%