	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 67.7%	2nd 68.0%	- -	1st 68.2%	5th 61.0%	4th 67.5%
44.2%	44%	53%		45%	18%	61%
59.2%	65%	67%		47%	61%	56%
78.4%	87%	80%		77%	71%	77%
82.4%	79%	84%		86%	80%	83%
61.6%	66%	71%		68%	48%	55%
49.8%	44%	73%		44%	44%	44%
68.4%	68%	70%		70%	63%	71%
71.8%	90%	49%		77%	73%	70%
68.2%	72%	65%		61%	69%	74%
83.8%	86%	94%		83%	78%	78%
56.6%	63%	73%		58%	38%	51%
52.4%	47%	53%		53%	54%	55%
73.2%	79%	77%		78%	61%	71%
76.0%	72%	72%		77%	79%	80%
80.4%	76%	81%		83%	74%	88%
50.6%	44%	57%		57%	38%	57%
65.2%	73%	60%		62%	63%	68%
73.0%	76%	73%		74%	71%	71%
72.6%	75%	78%		77%	67%	66%
66.6%	78%	69%		68%	50%	68%
58.4%	59%	62%		62%	59%	50%
55.4%	61%	46%		73%	30%	67%
90.6%	93%	95%		79%	93%	93%
56.8%	55%	60%		56%	57%	56%
86.4%	90%	82%		89%	78%	93%
62.4%	63%	67%		69%	46%	67%
56.0%	61%	24%		66%	66%	63%
48.8%	45%	39%		50%	45%	65%
97.2%	97%	99%		100%	97%	93%
66.8%	55%	70%		69%	70%	70%
49.2%	44%	54%		56%	38%	54%
66.6%	65%	67%		63%	69%	69%
71.2%	73%	83%		68%	70%	62%
73.6%	72%	84%		79%	71%	62%
63.4%	66%	71%		59%	65%	56%
71.8%	67%	75%		74%	69%	74%
57.6%	51%	58%		57%	57%	65%
57.0%	59%	55%		61%	55%	55%
56.6%	62%	60%		67%	37%	57%
67.2%	67%	62%		69%	69%	69%
73.2%	81%	75%		76%	59%	75%
70.4%	72%	67%		73%	61%	79%
59.8%	66%	66%		61%	56%	50%
64.0%	63%	65%		74%	45%	73%
77.4%	83%	80%		70%	79%	75%
65.6%	59%	63%		71%	64%	71%