	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 70.8%	1st 74.1%	6th 66.6%	3rd 70.8%	4th 68.9%	5th 67.1%
75.5%	76%	79%	70%	76%	76%	76%
74.0%	74%	70%	78%	74%	73%	75%
69.0%	67%	70%	76%	72%	57%	72%
68.8%	69%	71%	71%	72%	69%	61%
88.3%	93%	87%	90%	87%	88%	85%
65.3%	67%	71%	66%	68%	61%	59%
77.3%	74%	85%	74%	81%	75%	75%
62.8%	61%	62%	45%	73%	73%	63%
82.7%	82%	87%	74%	81%	87%	85%
80.0%	84%	78%	81%	84%	79%	74%
88.2%	91%	84%	89%	91%	87%	87%
80.7%	79%	92%	80%	79%	79%	75%
78.3%	83%	75%	92%	81%	58%	81%
69.7%	78%	63%	56%	68%	78%	75%
70.8%	76%	72%	67%	69%	71%	70%
64.2%	65%	72%	55%	65%	63%	65%
61.7%	71%	72%	53%	66%	48%	60%
52.5%	56%	68%	38%	56%	52%	45%
43.0%	35%	66%	32%	41%	56%	28%
83.5%	75%	88%	82%	89%	87%	80%
81.8%	91%	89%	74%	83%	82%	72%
73.5%	78%	83%	65%	72%	71%	72%
64.3%	57%	67%	68%	67%	57%	70%
77.7%	81%	84%	75%	76%	72%	78%
69.2%	71%	65%	67%	72%	70%	70%
72.5%	67%	72%	72%	74%	78%	72%
55.3%	59%	64%	45%	52%	56%	56%
51.3%	58%	71%	37%	42%	54%	46%
73.5%	84%	76%	69%	78%	71%	63%
61.0%	56%	82%	53%	64%	58%	53%
59.8%	61%	69%	56%	55%	62%	56%
62.7%	68%	64%	62%	59%	57%	66%
50.2%	50%	53%	58%	58%	41%	41%
70.8%	71%		70%	74%	73%	66%
71.4%	75%		70%	70%	74%	68%
65.5%	72%	77%	54%	65%	66%	59%
71.2%	68%	56%	70%	72%	89%	72%
78.5%	84%	79%	90%	82%	66%	70%
52.8%	44%	64%	46%	54%	61%	48%
96.5%	94%	98%	100%	97%	95%	95%
56.7%	54%	76%	53%	59%	49%	49%
77.2%	79%	82%	74%	74%	73%	81%
67.3%	67%	57%	65%	73%	72%	70%