	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%	4th 77.1%	- -	1st 79.1%	5th 73.6%	3rd 77.2%
64.0%	63%	65%		64%	58%	70%
72.2%	79%	71%		67%	76%	68%
66.4%	72%	74%		59%	73%	54%
78.4%	80%	75%		75%	81%	81%
84.2%	87%	89%		84%	76%	85%
84.8%	83%	78%		86%	92%	85%
90.2%	91%	86%		92%	91%	91%
69.4%	62%	71%		74%	75%	65%
74.2%	74%	84%		76%	74%	63%
83.4%	89%	86%		81%	76%	85%
81.0%	83%	94%		79%	72%	77%
58.4%	56%	53%		63%	51%	69%
64.6%	68%	61%		82%	56%	56%
79.2%	81%	76%		76%	81%	82%
73.0%	75%	66%		75%	76%	73%
69.6%	79%	84%		72%	49%	64%
82.6%	89%	85%		85%	73%	81%
86.8%	87%	85%		85%	88%	89%
81.4%	80%	88%		81%	80%	78%
70.0%	78%	76%		76%	44%	76%
80.6%	82%	84%		81%	70%	86%
65.8%	85%	0%		72%	84%	88%
87.8%	85%	83%		89%	98%	84%
79.2%	78%	83%		77%	75%	83%
61.4%	65%	57%		79%	53%	53%
76.6%	71%	77%		83%	66%	86%
87.6%	89%	88%		87%	82%	92%
78.2%	69%	78%		86%	69%	89%
90.8%	90%	84%		94%	87%	99%
77.6%	77%	81%		80%	78%	72%
68.6%	67%	83%		69%	55%	69%
72.4%	71%	74%		72%	72%	73%
82.2%	88%	86%		79%	75%	83%
77.6%	74%	81%		91%	74%	68%
79.8%	80%	75%		83%	83%	78%
90.2%	85%	98%		86%	89%	93%
81.4%	78%	84%		82%	82%	81%
74.4%	82%	73%		79%	70%	68%
68.8%	70%	74%		80%	48%	72%
82.2%	91%	82%		84%	76%	78%
85.6%	91%	89%		89%	71%	88%
79.0%	81%	70%		79%	84%	81%
69.8%	72%	68%		75%	69%	65%
73.8%	67%	74%		76%	76%	76%
83.6%	88%	88%		75%	82%	85%
79.6%	88%	85%		78%	77%	70%