	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 69.0%	1st 70.1%	6th 57.0%	3rd 66.4%	5th 63.6%	4th 66.2%
77.4%	83%	77%		73%	77%	77%
75.8%	82%	42%		84%	88%	83%
76.4%	75%	69%		81%	82%	75%
34.2%	36%	36%		39%	20%	40%
83.0%	81%	85%		82%	83%	84%
70.8%	76%	81%		64%	64%	69%
69.2%	64%	80%		71%	60%	71%
71.6%	73%	85%		66%	68%	66%
89.6%	82%	100%		89%	83%	94%
40.8%	41%	56%	44%	46%	9%	49%
85.4%	84%	89%		78%	88%	88%
33.6%	30%	47%		28%	27%	36%
78.6%	88%	80%		76%	73%	76%
88.4%	95%	89%		87%	87%	84%
70.8%	70%	72%	54%	69%	90%	70%
61.8%	64%	67%		58%	60%	60%
52.4%	61%	61%		48%	46%	46%
61.2%	67%	65%		67%	61%	46%
67.0%	72%	53%		72%	71%	67%
60.8%	56%	75%		60%	58%	55%
79.0%	89%	73%		83%	80%	70%
78.0%	75%	87%		72%	84%	72%
69.2%	77%	70%		70%	45%	84%
70.8%	79%	66%		77%	61%	71%
59.2%	61%	62%		55%	61%	57%
65.0%	64%	65%		62%	60%	74%
59.8%	62%	64%		50%	68%	55%
52.4%	54%	81%		45%	49%	33%
37.8%	38%	39%		33%	33%	46%
59.2%	56%	69%		66%	54%	51%
76.4%	80%	81%		72%	78%	71%
75.2%	79%	73%		73%	72%	79%
55.4%	53%	58%		58%	55%	53%
77.0%	79%	81%	73%	78%	78%	73%
50.4%	64%	32%		52%	32%	72%
74.6%	77%	87%		82%	69%	58%
70.8%	72%	71%		70%	70%	71%
87.2%	85%	80%		89%	94%	88%
49.6%	58%	56%		44%	45%	45%
92.2%	89%	94%		98%	91%	89%
69.6%	70%	94%		63%	54%	67%
53.8%	51%	56%		54%	52%	56%
69.4%	77%	67%		73%	56%	74%