	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 75.5%	4th 72.7%	- -	1st 75.6%	5th 67.9%	3rd 74.6%
78.6%	79%	78%		79%	75%	82%
69.0%	59%	57%		80%	77%	72%
59.0%	50%	59%		63%	67%	56%
89.8%	88%	93%		94%	81%	93%
71.6%	74%	86%		70%	59%	69%
94.4%	96%	99%		95%	90%	92%
79.8%	85%	86%		80%	63%	85%
74.4%	78%	73%		77%	73%	71%
72.8%	73%	67%		79%	67%	78%
74.6%	76%	67%		78%	81%	71%
78.0%	83%	69%		87%	76%	75%
72.4%	71%	70%		73%	75%	73%
76.4%	83%	79%		84%	57%	79%
81.6%	88%	88%		77%	67%	88%
71.8%	77%	73%		77%	62%	70%
67.8%	71%	68%		67%	70%	63%
59.0%	70%	57%		73%	33%	62%
76.2%	78%	69%		78%	81%	75%
37.0%	38%	65%		37%	16%	29%
82.2%	74%	82%		85%	82%	88%
69.4%	71%	68%		71%	66%	71%
82.8%	88%	88%		74%	83%	81%
79.2%	76%	92%		82%	53%	93%
69.0%	78%	74%		72%	56%	65%
72.2%	75%	73%		63%	73%	77%
66.2%	71%	58%		68%	62%	72%
65.6%	67%	75%		56%	62%	68%
64.4%	69%	73%		67%	58%	55%
66.2%	73%	76%		59%	64%	59%
74.0%	81%	65%		75%	68%	81%
60.8%	66%	63%		61%	56%	58%
87.2%	80%	86%		90%	90%	90%
92.8%	92%	97%		94%	84%	97%
85.2%	89%	72%		91%	79%	95%
73.6%	86%	32%		92%	72%	86%
66.8%	69%	54%		73%	69%	69%
58.6%	57%	62%		62%	54%	58%
74.2%	76%	92%		78%	50%	75%
66.6%	72%	61%		68%	66%	66%
94.8%	98%	91%		95%	90%	100%
66.8%	70%	58%		72%	70%	64%
75.4%	78%	71%		77%	71%	80%
71.8%	73%	58%		78%	73%	77%