	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 73.7%	1st 73.7%	- -	3rd 73.3%	5th 65.9%	4th 71.4%
46.0%	49%	41%		41%	40%	59%
59.4%	61%	63%		54%	63%	56%
62.0%	62%	68%		60%	60%	60%
74.4%	76%	74%		71%	77%	74%
78.6%	81%	85%		76%	73%	78%
76.8%	71%	92%		79%	79%	63%
79.2%	84%	85%		76%	75%	76%
69.8%	76%	57%		76%	73%	67%
71.0%	68%	81%		74%	64%	68%
76.2%	83%	79%		76%	69%	74%
64.2%	64%	79%		66%	49%	63%
66.0%	64%	52%		74%	66%	74%
72.2%	65%	87%		85%	46%	78%
73.6%	75%	73%		70%	76%	74%
70.4%	73%	63%		72%	72%	72%
49.8%	57%	49%		54%	33%	56%
80.6%	85%	82%		82%	86%	68%
78.0%	73%	80%		81%	81%	75%
77.0%	76%	87%		78%	73%	71%
57.6%	62%	79%		62%	32%	53%
66.0%	61%	66%		71%	61%	71%
66.4%	79%	56%		57%	63%	77%
93.2%	92%	93%		85%	98%	98%
85.2%	88%	74%		86%	86%	92%
66.0%	58%	81%		79%	40%	72%
58.0%	56%	60%		68%	38%	68%
73.2%	73%	61%		77%	74%	81%
70.4%	76%	61%		73%	62%	80%
89.6%	86%	92%		89%	91%	90%
65.0%	68%	71%		59%	68%	59%
48.0%	51%	47%		55%	38%	49%
68.0%	68%	71%		67%	67%	67%
78.0%	84%	86%		78%	68%	74%
76.8%	80%	88%		69%	74%	73%
83.2%	87%	84%		89%	75%	81%
87.2%	87%	92%		89%	85%	83%
71.6%	74%	76%		67%	67%	74%
75.0%	81%	67%		77%	69%	81%
60.0%	62%	73%		72%	32%	61%
74.4%	84%	79%		79%	63%	67%
79.8%	87%	79%		81%	77%	75%
77.0%	79%	69%		86%	76%	75%
58.6%	61%	62%		61%	61%	48%
74.6%	82%	77%		79%	64%	71%
83.6%	91%	86%		87%	70%	84%
81.2%	88%	81%		84%	77%	76%