	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 78.7%	1st 79.4%	- -	3rd 78.1%	5th 72.7%	4th 78.1%
66.4%	73%	65%		66%	55%	73%
68.8%	77%	76%		61%	74%	56%
68.4%	71%	76%		71%	69%	55%
81.0%	83%	77%		81%	81%	83%
85.6%	94%	89%		90%	68%	87%
82.8%	71%	91%		79%	93%	80%
90.4%	88%	91%		89%	92%	92%
72.4%	76%	65%		68%	75%	78%
78.2%	80%	91%		76%	67%	77%
80.4%	82%	91%		76%	76%	77%
68.2%	69%	77%		71%	54%	70%
64.4%	59%	61%		71%	54%	77%
81.8%	78%	90%		83%	79%	79%
79.4%	82%	74%		78%	81%	82%
73.0%	70%	72%		69%	77%	77%
58.4%	67%	58%		60%	47%	60%
84.2%	91%	88%		86%	75%	81%
82.0%	84%	86%		82%	85%	73%
75.8%	76%	83%		76%	75%	69%
62.6%	65%	73%		66%	42%	67%
83.0%	81%	85%		91%	74%	84%
70.4%	78%	56%		65%	67%	86%
96.6%	99%	99%		88%	99%	98%
83.6%	85%	87%		79%	82%	85%
79.4%	76%	86%		81%	77%	77%
66.2%	62%	75%		70%	51%	73%
86.6%	88%	71%		93%	85%	96%
83.0%	83%	70%		90%	79%	93%
96.6%	95%	95%		99%	98%	96%
76.4%	66%	83%		73%	84%	76%
67.4%	69%	77%		69%	51%	71%
67.4%	64%	68%		69%	67%	69%
76.0%	78%	81%		73%	74%	74%
80.6%	81%	89%		81%	68%	84%
85.8%	88%	92%		88%	80%	81%
88.6%	87%	83%		87%	94%	92%
73.0%	71%	80%		71%	67%	76%
73.0%	79%	72%		76%	62%	76%
63.6%	69%	59%		74%	50%	66%
85.8%	94%	80%		91%	81%	83%
82.6%	90%	85%		86%	67%	85%
82.2%	82%	83%		86%	76%	84%
64.0%	69%	69%		61%	66%	55%
70.2%	71%	72%		79%	59%	70%
89.4%	90%	92%		91%	79%	95%
85.0%	90%	90%		84%	86%	75%