	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 69.4%	1st 70.6%	- -	3rd 66.2%	5th 62.5%	4th 65.1%
77.2%	83%	77%		80%	77%	69%
83.6%	82%	78%		84%	88%	86%
75.8%	75%	81%		75%	73%	75%
33.0%	36%	31%		38%	20%	40%
82.4%	82%	84%		82%	80%	84%
73.2%	81%	81%		67%	64%	73%
67.8%	64%	75%		71%	71%	58%
70.0%	73%	85%		65%	61%	66%
91.2%	93%	99%		92%	83%	89%
39.2%	41%	47%		47%	14%	47%
84.8%	84%	85%		78%	88%	89%
32.0%	36%	44%		35%	9%	36%
78.2%	88%	80%		75%	72%	76%
88.4%	95%	89%		87%	87%	84%
73.8%	70%	72%		67%	90%	70%
58.6%	62%	67%		52%	60%	52%
53.0%	61%	70%		42%	46%	46%
59.0%	65%	65%		58%	61%	46%
67.0%	72%	53%		72%	71%	67%
60.4%	55%	75%		59%	58%	55%
75.8%	89%	73%		72%	75%	70%
79.2%	78%	83%		79%	84%	72%
72.2%	77%	83%		72%	45%	84%
69.6%	79%	64%		75%	59%	71%
59.0%	61%	62%		55%	60%	57%
67.0%	64%	65%		70%	60%	76%
60.4%	62%	69%		48%	68%	55%
48.0%	54%	71%		33%	49%	33%
37.0%	38%	39%		55%	7%	46%
58.2%	56%	61%		69%	54%	51%
74.4%	77%	78%		68%	78%	71%
75.4%	79%	73%		70%	76%	79%
56.2%	53%	58%		58%	59%	53%
71.4%	77%	81%		78%	62%	59%
51.2%	64%	32%		56%	32%	72%
73.8%	77%	88%		82%	69%	53%
72.2%	72%	66%		72%	80%	71%
85.6%	85%	80%		89%	86%	88%
48.4%	58%	53%		41%	45%	45%
90.4%	89%	94%		89%	91%	89%
72.4%	70%	100%		63%	62%	67%
56.0%	52%	56%		54%	62%	56%
68.2%	77%	67%		73%	50%	74%