	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 67.3%	5th 61.8%	1st 68.0%	3rd 64.3%	6th 60.3%	4th 63.0%
57.0%	60%	48%		59%	60%	58%
36.2%	30%	0%		58%	43%	50%
84.0%	82%	75%		92%	79%	92%
58.8%	66%	55%		55%	55%	63%
79.2%	78%	87%		83%	71%	77%
81.4%	74%	86%		74%	87%	86%
47.4%	44%	45%		49%	55%	44%
61.0%	65%	77%		58%	58%	47%
65.8%	64%	64%		67%	66%	68%
60.0%	80%	55%		55%	55%	55%
48.4%	60%	20%		49%	64%	49%
74.6%	75%	80%		71%	80%	67%
75.0%	76%	73%		86%	58%	82%
60.4%	54%	58%		61%	59%	70%
46.8%	46%	49%		55%	29%	55%
56.0%	55%	67%		49%	51%	58%
59.2%	77%	55%		64%	45%	55%
61.4%	58%	75%		58%	58%	58%
45.0%	53%	48%		34%	32%	58%
56.4%	66%	64%		56%	49%	47%
79.4%	79%	74%		79%	76%	89%
68.8%	75%	67%	68%	75%	63%	65%
49.6%	45%	45%		50%	51%	57%
65.0%	72%	65%		72%	51%	65%
51.2%	59%	56%		51%	58%	32%
60.6%	61%	68%		57%	60%	57%
59.4%	71%	69%		38%	69%	50%
55.4%	67%	45%		63%	58%	44%
60.2%	71%	64%		56%	64%	46%
71.2%	80%	56%		74%	67%	79%
76.0%	88%	78%		76%	65%	73%
73.8%	79%	86%		68%	68%	68%
72.0%	70%	63%		80%	67%	80%
53.0%	52%	55%		54%	49%	55%
61.0%	69%	40%		54%	69%	73%
55.4%	62%	23%		67%	63%	62%
74.6%	74%	90%		85%	53%	71%
74.0%	75%	90%		80%	59%	66%
54.8%	62%	59%		54%	54%	45%
90.8%	98%	95%		87%	87%	87%
51.4%	53%	58%		53%	43%	50%
84.0%	90%	86%		83%	70%	91%
66.4%	78%	43%		75%	73%	63%