	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 74.7%	1st 77.3%	- -	3rd 72.4%	5th 68.9%	4th 70.8%
51.4%	53%	53%		53%	55%	43%
84.0%	83%	80%		87%	78%	92%
82.2%	92%	82%		83%	78%	76%
70.2%	72%	70%		74%	64%	71%
63.2%	74%	50%		61%	54%	77%
75.4%	78%	78%		81%	72%	68%
83.0%	86%	84%		80%	82%	83%
59.6%	67%	95%		52%	42%	42%
75.4%	75%	91%		73%	66%	72%
71.4%	73%	81%		68%	74%	61%
92.0%	89%	97%		89%	91%	94%
79.6%	75%	64%		85%	85%	89%
58.8%	65%	81%		58%	45%	45%
84.8%	90%	89%		83%	79%	83%
78.2%	84%	86%		81%	71%	69%
84.8%	90%	84%		87%	75%	88%
73.2%	73%	79%		77%	70%	67%
71.2%	70%	89%		68%	58%	71%
55.6%	53%	73%		56%	45%	51%
69.0%	72%	77%		67%	73%	56%
81.2%	84%	85%		77%	84%	76%
80.4%	90%	87%		77%	80%	68%
55.4%	59%	48%		44%	80%	46%
78.2%	82%	77%		82%	76%	74%
81.2%	85%	89%		78%	75%	79%
83.8%	88%	85%		79%	81%	86%
95.6%	98%	85%		98%	97%	100%
72.4%	77%	96%		62%	72%	55%
76.8%	84%	80%		80%	70%	70%
46.6%	41%	50%		55%	40%	47%
71.2%	71%	66%		73%	70%	76%
64.2%	61%	65%		66%	54%	75%
66.4%	69%	77%		58%	67%	61%
77.2%	76%	68%		81%	79%	82%
39.2%	31%	46%		38%	38%	43%
83.0%	85%	83%		84%	82%	81%
77.2%	82%	82%		76%	74%	72%
46.0%	41%	65%		45%	36%	43%
86.0%	90%	84%		80%	88%	88%
86.2%	84%	92%		87%	90%	78%
82.2%	82%	81%		83%	86%	79%
63.2%	71%	70%		56%	63%	56%
68.4%	67%	85%		66%	58%	66%
90.0%	89%	96%		91%	82%	92%
74.8%	77%	73%		74%	77%	73%
54.6%	49%	57%		49%	49%	69%
49.6%	47%	64%		58%	30%	49%
69.2%	74%	76%		69%	65%	62%
72.0%	78%	82%		70%	62%	68%
76.6%	83%	84%		82%	58%	76%
79.4%	84%	87%		75%	71%	80%
82.6%	84%	78%		80%	82%	89%
84.8%	90%	87%		89%	77%	81%
74.4%	69%	61%		87%	71%	84%