	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 74.7%	1st 75.2%	- -	3rd 71.5%	5th 68.2%	4th 70.7%
65.4%	77%	66%		61%	63%	60%
85.4%	85%	88%		90%	73%	91%
90.2%	93%	97%		97%	74%	90%
80.6%	89%	86%		79%	70%	79%
62.2%	71%	47%		56%	59%	78%
64.0%	59%	69%		68%	61%	63%
78.8%	80%	84%		78%	80%	72%
62.6%	78%	94%		39%	63%	39%
67.0%	71%	62%		72%	64%	66%
66.8%	65%	74%		60%	74%	61%
83.4%	85%	81%		89%	86%	76%
80.2%	73%	67%		80%	88%	93%
54.4%	69%	82%		64%	14%	43%
86.2%	90%	86%		88%	78%	89%
85.6%	91%	87%		82%	85%	83%
84.0%	85%	90%		85%	73%	87%
79.6%	85%	81%		82%	80%	70%
77.4%	76%	91%		75%	71%	74%
44.2%	59%	48%		44%	23%	47%
79.4%	79%	87%		76%	87%	68%
81.4%	81%	81%		76%	93%	76%
81.2%	86%	85%		80%	80%	75%
59.8%	66%	66%		45%	70%	52%
70.4%	76%	69%		71%	70%	66%
89.0%	88%	86%		87%	92%	92%
87.0%	93%	91%		86%	82%	83%
90.6%	84%	85%		95%	93%	96%
64.0%	72%	71%		51%	71%	55%
82.4%	87%	79%		85%	85%	76%
49.4%	54%	56%		53%	31%	53%
77.8%	74%	78%		77%	75%	85%
58.6%	60%	53%		56%	56%	68%
67.2%	68%	70%		58%	75%	65%
77.6%	76%	79%		75%	79%	79%
32.8%	36%	34%		31%	27%	36%
85.0%	80%	93%		83%	90%	79%
73.6%	75%	73%		72%	77%	71%
41.4%	41%	43%		41%	41%	41%
80.4%	79%	77%		86%	84%	76%
79.4%	74%	86%		77%	87%	73%
82.2%	77%	87%		82%	87%	78%
71.6%	77%	78%		63%	74%	66%
62.0%	48%	83%		64%	61%	54%
81.0%	86%	85%		86%	75%	73%
75.2%	72%	72%		78%	70%	84%
50.4%	58%	55%		50%	28%	61%
45.4%	60%	51%		58%	13%	45%
54.4%	56%	57%		54%	57%	48%
74.8%	83%	84%		69%	64%	74%
65.4%	72%	73%		73%	35%	74%
81.2%	90%	86%		80%	66%	84%
82.2%	83%	76%		85%	85%	82%
86.2%	87%	85%		92%	82%	85%
72.6%	77%	66%		76%	62%	82%