	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 82.6%	1st 82.6%	- -	3rd 78.1%	4th 75.2%	5th 74.8%
55.2%	60%	49%		60%	62%	45%
82.2%	92%	93%		82%	71%	73%
74.4%	84%	79%		75%	69%	65%
71.4%	72%	75%		69%	73%	68%
73.8%	86%	87%		60%	73%	63%
73.8%	90%	88%		84%	55%	52%
90.8%	95%	94%		90%	83%	92%
58.0%	62%	96%		38%	49%	45%
65.0%	66%	67%		70%	57%	65%
79.0%	84%	81%		77%	80%	73%
92.0%	88%	88%		94%	93%	97%
88.2%	88%	93%		82%	89%	89%
52.2%	65%	81%		57%	29%	29%
86.6%	88%	80%		89%	86%	90%
86.6%	88%	87%		92%	83%	83%
86.6%	94%	92%		98%	71%	78%
78.6%	80%	87%		78%	73%	75%
80.4%	86%	93%		80%	67%	76%
84.6%	91%	88%		81%	83%	80%
73.4%	78%	76%		73%	78%	62%
86.0%	84%	91%		82%	83%	90%
89.6%	95%	92%		93%	88%	80%
58.2%	69%	58%		43%	73%	48%
82.6%	88%	91%		87%	76%	71%
84.6%	83%	91%		86%	76%	87%
89.2%	96%	93%		94%	71%	92%
90.0%	91%	87%		91%	92%	89%
75.0%	82%	88%		70%	76%	59%
83.0%	87%	81%		91%	83%	73%
83.8%	89%	89%		63%	89%	89%
60.4%	50%	82%		58%	54%	58%
83.4%	88%	81%		87%	77%	84%
81.4%	83%	84%		79%	82%	79%
81.6%	81%	81%		81%	79%	86%
65.8%	70%	82%		61%	65%	51%
86.4%	94%	94%		85%	81%	78%
80.6%	85%	81%		78%	81%	78%
78.2%	81%	80%		79%	81%	70%
84.0%	79%	73%		88%	86%	94%
87.2%	86%	88%		82%	91%	89%
81.6%	85%	84%		80%	79%	80%
75.8%	82%	83%		67%	74%	73%
74.6%	83%	78%		76%	67%	69%
84.6%	83%	87%		90%	81%	82%
82.0%	87%	82%		72%	83%	86%
84.8%	78%	83%		91%	89%	83%
61.2%	81%	67%		59%	47%	52%
66.2%	73%	68%		62%	69%	59%
77.8%	84%	75%		82%	72%	76%
79.0%	66%	92%		80%	72%	85%
87.8%	92%	86%		92%	78%	91%
87.4%	93%	83%		89%	86%	86%
88.6%	88%	90%		88%	86%	91%
72.8%	88%	43%		81%	70%	82%