	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	2nd 67.6%	5th 63.3%	- -	1st 68.1%	4th 64.2%	3rd 65.3%
75.8%	71%	77%		72%	77%	82%
64.6%	58%	61%		62%	75%	67%
69.0%	91%	62%		71%	61%	60%
100.0%	100%	100%		100%	100%	100%
85.4%	84%	79%		100%	72%	92%
51.6%	36%	56%		56%	55%	55%
76.0%	79%	85%		75%	77%	64%
40.8%	36%	70%		32%	31%	35%
54.8%	63%	58%		64%	45%	44%
73.4%	73%	76%		80%	67%	71%
61.8%	70%	69%		60%	60%	50%
46.8%	51%	41%		56%	34%	52%
72.0%	66%	70%		66%	81%	77%
100.0%	100%	100%		100%	100%	100%
64.6%	69%	56%		66%	67%	65%
60.6%	58%	62%		67%	54%	62%
70.0%	70%	70%		70%	70%	70%
84.0%	82%	75%		91%	87%	85%
65.4%	70%	56%		71%	60%	70%
44.8%	62%	37%		53%	36%	36%
69.2%	78%	58%		76%	69%	65%
71.6%	81%	26%		84%	75%	92%
94.6%	95%	93%		92%	93%	100%
38.8%	42%	35%		33%	46%	38%
72.0%	66%	70%		66%	81%	77%
48.2%	51%	43%		56%	46%	45%
37.2%	40%	0%		47%	48%	51%
62.2%	73%	51%		67%	54%	66%
92.8%	87%	93%		85%	100%	99%
50.6%	47%	54%		60%	46%	46%
77.4%	79%	77%		79%	77%	75%
68.2%	65%	70%		71%	72%	63%
68.0%	67%	63%		79%	65%	66%
58.2%	59%	70%		54%	52%	56%
47.8%	47%	50%		47%	48%	47%
64.8%	61%	77%		61%	61%	64%
56.8%	61%	49%		62%	58%	54%
41.8%	45%	49%		36%	41%	38%
49.4%	51%	43%		62%	43%	48%
80.8%	78%	80%		78%	84%	84%
70.2%	79%	70%		70%	62%	70%
61.4%	62%	69%		59%	66%	51%
68.8%	83%	66%		75%	57%	63%
65.0%	68%	57%		71%	64%	65%
67.4%	73%	62%		73%	62%	67%
77.4%	81%	78%		77%	73%	78%