	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 74.9%	1st 77.8%	- -	3rd 73.7%	5th 65.0%	4th 73.2%
54.2%	46%	63%		52%	46%	64%
64.2%	69%	73%		58%	64%	57%
56.8%	63%	69%		53%	47%	52%
72.6%	75%	68%		72%	75%	73%
78.0%	81%	79%		76%	75%	79%
74.4%	66%	88%		73%	80%	65%
84.6%	81%	85%		86%	86%	85%
69.8%	75%	62%		77%	68%	67%
67.4%	67%	85%		65%	54%	66%
80.0%	84%	84%		80%	76%	76%
71.6%	70%	93%		74%	53%	68%
69.0%	70%	81%		68%	51%	75%
81.8%	92%	99%		88%	49%	81%
71.0%	73%	69%		70%	74%	69%
69.2%	68%	67%		69%	71%	71%
58.0%	58%	79%		56%	39%	58%
76.0%	84%	73%		77%	78%	68%
80.8%	84%	82%		81%	81%	76%
76.8%	81%	81%		74%	75%	73%
64.4%	68%	73%		69%	45%	67%
69.8%	68%	72%		71%	63%	75%
67.8%	75%	51%		71%	58%	84%
95.4%	99%	94%		86%	99%	99%
85.2%	79%	93%		81%	83%	90%
75.2%	86%	92%		81%	43%	74%
58.6%	56%	70%		60%	37%	70%
79.2%	74%	68%		84%	88%	82%
74.8%	80%	68%		83%	61%	82%
92.0%	86%	97%		90%	97%	90%
64.8%	70%	72%		60%	67%	55%
52.6%	46%	56%		56%	47%	58%
67.6%	69%	71%		69%	62%	67%
74.2%	75%	75%		75%	73%	73%
66.4%	65%	92%		58%	57%	60%
77.0%	87%	78%		91%	48%	81%
85.6%	82%	88%		86%	85%	87%
74.4%	80%	79%		65%	68%	80%
75.4%	83%	78%		80%	65%	71%
63.6%	66%	75%		77%	34%	66%
70.8%	79%	70%		75%	64%	66%
77.2%	85%	80%		75%	71%	75%
76.0%	75%	79%		84%	52%	90%
65.4%	73%	76%		63%	62%	53%
74.0%	69%	77%		80%	64%	80%
88.6%	94%	94%		86%	76%	93%
81.0%	88%	81%		85%	77%	74%