	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 71.4%	1st 71.9%	- -	3rd 67.0%	5th 62.3%	4th 65.1%
66.2%	73%	62%		60%	76%	60%
73.4%	74%	79%		75%	70%	69%
84.4%	87%	100%		82%	70%	83%
74.2%	86%	74%		67%	65%	79%
66.8%	80%	28%		64%	88%	74%
52.4%	68%	48%		50%	48%	48%
77.6%	76%	75%		81%	75%	81%
57.8%	61%	100%		32%	56%	40%
53.4%	59%	53%		57%	41%	57%
85.4%	87%	94%		84%	88%	74%
80.4%	93%	75%		88%	61%	85%
83.0%	80%	78%		82%	89%	86%
63.2%	79%	100%		72%	23%	42%
68.0%	70%	70%		66%	67%	67%
53.8%	55%	49%		52%	58%	55%
71.8%	70%	71%		74%	72%	72%
75.6%	83%	63%		85%	68%	79%
55.0%	50%	79%		50%	53%	43%
59.2%	61%	63%		56%	63%	53%
69.8%	65%	75%		60%	83%	66%
75.8%	76%	84%		79%	63%	77%
80.8%	80%	88%		75%	77%	84%
67.6%	70%	66%		51%	100%	51%
60.8%	62%	71%		65%	59%	47%
66.8%	69%	67%		73%	57%	68%
71.0%	79%	79%		79%	49%	69%
90.8%	96%	90%		94%	82%	92%
55.0%	66%	81%		42%	50%	36%
76.6%	86%	78%		78%	70%	71%
70.4%	71%	73%		77%	67%	64%
43.4%	39%	64%		46%	20%	48%
72.2%	74%	75%		75%	60%	77%
78.2%	76%	80%		69%	82%	84%
69.8%	69%	85%		66%	63%	66%
58.6%	67%	74%		60%	50%	42%
73.4%	69%	82%		82%	56%	78%
62.4%	76%	73%		48%	52%	63%
68.0%	59%	79%		60%	69%	73%
59.4%	52%	51%		73%	60%	61%
51.4%	50%	68%		48%	39%	52%
54.8%	58%	64%		56%	37%	59%
66.8%	71%	76%		58%	65%	64%
60.0%	71%	71%		55%	43%	60%
58.4%	72%	46%		70%	50%	54%
66.8%	66%	71%		66%	68%	63%
63.4%	65%	73%		60%	67%	52%
74.0%	91%	76%		76%	68%	59%
52.2%	67%	69%		40%	43%	42%
62.0%	64%	67%		65%	55%	59%
63.0%	64%	64%		61%	52%	74%
81.6%	89%	77%		89%	68%	85%
68.2%	71%	61%		76%	63%	70%
83.4%	82%	76%		85%	82%	92%
68.4%	79%	46%		82%	66%	69%