	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 68.5%	5th 62.2%	1st 82.0%	4th 66.5%	6th 61.0%	3rd 66.7%
39.6%	45%	36%		44%	25%	48%
67.4%	78%	67%		55%	78%	59%
79.2%	81%	72%		71%	92%	80%
76.0%	77%	77%		71%	78%	77%
57.8%	60%	59%		58%	51%	61%
71.2%	67%	73%		70%	73%	73%
64.0%	59%	55%		64%	70%	72%
61.0%	59%	56%		71%	58%	61%
65.6%	75%	33%		75%	69%	76%
69.2%	78%	71%		65%	64%	68%
73.8%	78%	84%		76%	60%	71%
70.4%	74%	65%		71%	71%	71%
75.0%	88%	70%		92%	55%	70%
76.6%	77%	75%		76%	78%	77%
61.4%	83%	0%		69%	78%	77%
53.4%	67%	57%		55%	32%	56%
67.4%	79%	77%		64%	52%	65%
62.8%	61%	66%		63%	63%	61%
64.4%	65%	59%		69%	66%	63%
63.8%	62%	74%		72%	39%	72%
66.4%	63%	70%		70%	62%	67%
54.0%	71%	18%		46%	59%	76%
81.0%	82%	88%		73%	80%	82%
73.2%	74%	79%		67%	77%	69%
71.8%	85%	65%		85%	54%	70%
65.2%	66%	64%		68%	60%	68%
58.4%	58%	55%		62%	55%	62%
63.4%	72%	66%		61%	54%	64%
88.2%	83%	90%		86%	90%	92%
59.4%	67%	55%		59%	56%	60%
40.6%	51%	35%		46%	28%	43%
72.0%	76%	73%		69%	69%	73%
69.0%	73%	75%		68%	62%	67%
74.6%	70%	77%		77%	73%	76%
66.4%	69%	69%		74%	57%	63%
63.6%	65%	71%		52%	64%	66%
61.0%	61%	62%		64%	60%	58%
61.2%	64%	25%		64%	77%	76%
53.2%	58%	56%		66%	25%	61%
90.0%	83%	89%		90%	90%	98%
75.8%	79%	80%	82%	73%	69%	72%
58.0%	63%	63%		55%	60%	49%
53.4%	57%	54%		54%	56%	46%
43.6%	41%	44%		49%	35%	49%
58.2%	56%	60%		73%	33%	69%
48.8%	52%	52%		56%	48%	36%