	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 72.1%	3rd 69.1%	1st 74.0%	4th 68.6%	6th 63.1%	5th 67.3%
74.6%	84%	68%		76%	71%	74%
69.0%	79%	67%	74%	67%	60%	67%
76.4%	79%	90%		81%	64%	68%
66.0%	69%	73%		66%	57%	65%
65.8%	69%	62%		70%	70%	58%
76.2%	72%	79%		81%	70%	79%
68.0%	72%	58%		72%	66%	72%
64.2%	77%	100%		39%	66%	39%
63.4%	60%	78%		65%	60%	54%
64.2%	67%	68%		60%	60%	66%
59.0%	53%	63%		61%	59%	59%
63.6%	65%	51%		65%	63%	74%
54.8%	61%	72%		58%	41%	42%
68.0%	76%	68%		69%	58%	69%
72.4%	77%	72%		73%	63%	77%
81.8%	95%	74%		89%	61%	90%
74.8%	78%	73%		75%	77%	71%
84.0%	89%	76%		78%	91%	86%
52.2%	49%	59%		57%	35%	61%
80.8%	81%	87%		82%	82%	72%
69.4%	79%	69%		75%	53%	71%
70.0%	78%	71%		67%	60%	74%
54.4%	59%	64%		38%	73%	38%
60.6%	62%	54%		55%	64%	68%
68.2%	78%	77%		62%	53%	71%
59.4%	72%	59%		66%	41%	59%
74.6%	85%	75%		71%	72%	70%
58.4%	56%	68%		61%	58%	49%
68.0%	68%	71%		67%	67%	67%
77.2%	83%	82%		82%	64%	75%
62.8%	66%	63%		62%	70%	53%
52.6%	50%	47%		48%	54%	64%
50.6%	49%	54%		49%	47%	54%
71.6%	75%	69%		69%	67%	78%
50.0%	52%	46%		46%	57%	49%
73.4%	78%	68%		75%	67%	79%
74.6%	78%	73%		74%	73%	75%
65.0%	62%	65%		67%	66%	65%
62.4%	65%	54%		60%	64%	69%
78.4%	78%	73%		77%	81%	83%
81.8%	86%	69%		85%	90%	79%
64.2%	69%	67%		59%	71%	55%
78.2%	82%	79%		81%	69%	80%
76.2%	88%	65%		95%	63%	70%
92.0%	91%	92%		95%	88%	94%
74.2%	83%	77%		90%	58%	63%
49.6%	61%	56%		49%	26%	56%
60.0%	63%	66%		58%	59%	54%
84.0%	88%	91%		88%	76%	77%
59.2%	66%	70%		70%	27%	63%
71.0%	80%	74%		80%	49%	72%
70.2%	79%	64%		67%	70%	71%
67.4%	60%	73%		58%	75%	71%
66.4%	73%	47%		75%	62%	75%