	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	1st 71.3%	3rd 68.2%	- -	2nd 70.2%	5th 63.4%	4th 67.5%
65.8%	69%	71%		63%	61%	65%
67.0%	64%	57%		78%	71%	65%
79.2%	78%	76%		83%	81%	78%
71.4%	70%	69%		79%	62%	77%
72.6%	73%	78%		67%	75%	70%
75.8%	84%	84%		73%	67%	71%
77.2%	83%	71%		76%	78%	78%
64.0%	67%	68%		63%	61%	61%
93.0%	96%	91%		93%	91%	94%
45.4%	55%	51%		51%	15%	55%
74.6%	80%	72%		80%	61%	80%
48.0%	57%	51%		51%	32%	49%
68.0%	72%	71%		68%	61%	68%
81.2%	83%	70%		81%	81%	91%
71.4%	73%	73%		76%	66%	69%
69.8%	72%	75%		74%	67%	61%
59.6%	69%	71%		57%	47%	54%
47.8%	53%	59%		51%	45%	31%
58.2%	67%	58%		55%	54%	57%
83.2%	85%	76%		86%	86%	83%
59.2%	53%	63%		63%	53%	64%
72.6%	73%	67%		76%	70%	77%
72.0%	71%	68%		77%	64%	80%
75.2%	85%	73%		72%	73%	73%
84.2%	88%	81%		84%	84%	84%
58.8%	57%	59%		62%	58%	58%
71.4%	79%	76%		63%	76%	63%
63.4%	69%	74%		65%	56%	53%
53.2%	69%	56%		65%	13%	63%
60.0%	63%	75%		60%	50%	52%
84.0%	85%	84%		85%	81%	85%
78.8%	80%	80%		75%	82%	77%
53.6%	53%	51%		57%	52%	55%
70.0%	71%	75%		78%	63%	63%
52.4%	60%	32%		61%	44%	65%
53.6%	57%	34%		58%	58%	61%
58.8%	57%	59%		61%	56%	61%
65.4%	72%	70%		70%	57%	58%
85.2%	87%	90%		86%	86%	77%
80.4%	78%	79%		83%	84%	78%
74.0%	75%	73%		79%	72%	71%
56.8%	56%	55%		53%	62%	58%
72.2%	78%	65%		80%	69%	69%