	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 70.4%	5th 67.4%	- -	1st 71.5%	4th 67.4%	3rd 69.7%
76.4%	76%	72%		81%	81%	72%
43.0%	48%	7%		55%	49%	56%
76.8%	68%	69%		82%	86%	79%
75.2%	77%	73%		75%	78%	73%
78.8%	78%	84%		78%	78%	76%
69.0%	64%	65%		67%	77%	72%
68.8%	71%	59%		65%	77%	72%
70.6%	69%	73%		77%	74%	60%
63.0%	62%	58%		65%	65%	65%
75.4%	65%	78%		78%	78%	78%
76.6%	83%	83%		76%	64%	77%
63.4%	63%	60%		65%	64%	65%
63.4%	68%	64%		68%	45%	72%
66.4%	68%	68%		70%	62%	64%
78.6%	84%	79%		79%	62%	89%
67.2%	65%	63%		71%	71%	66%
71.0%	83%	71%		79%	50%	72%
57.0%	62%	71%		53%	53%	46%
36.4%	28%	64%		36%	26%	28%
72.8%	60%	76%		77%	76%	75%
70.8%	78%	68%		70%	56%	82%
78.4%	84%	68%		85%	70%	85%
76.0%	72%	84%		72%	74%	78%
56.6%	65%	56%		61%	36%	65%
63.2%	65%	65%		72%	56%	58%
48.8%	57%	42%		56%	41%	48%
69.4%	75%	73%		67%	68%	64%
81.4%	84%	68%		90%	86%	79%
79.6%	79%	100%		73%	77%	69%
59.6%	60%	81%		60%	56%	41%
70.8%	68%	72%		72%	64%	78%
52.6%	63%	59%		47%	44%	50%
76.8%	68%	69%		82%	86%	79%
73.0%	85%	52%		76%	76%	76%
69.4%	58%	47%		68%	89%	85%
69.2%	75%	36%		73%	77%	85%
84.2%	86%	86%		91%	83%	75%
54.8%	56%	69%		55%	49%	45%
83.2%	100%	64%		91%	84%	77%
85.8%	77%	78%		91%	95%	88%
68.0%	76%	55%		77%	66%	66%
75.2%	70%	74%		76%	74%	82%
82.6%	84%	95%		72%	76%	86%