	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 70.6%	6th 65.1%	4th 68.1%	1st 72.5%	5th 65.3%	3rd 70.3%
60.3%	65%	55%	62%	67%	46%	67%
59.5%	65%	37%	64%	76%	44%	71%
71.7%	67%	57%	72%	73%	84%	77%
62.8%	60%	49%	79%	63%	64%	62%
81.2%	76%	78%	71%	82%	87%	93%
87.8%	89%	77%	92%	89%	86%	94%
85.2%	87%	84%	83%	89%	84%	84%
77.5%	85%	70%	59%	84%	86%	81%
81.8%	83%	87%	78%	88%	76%	79%
65.2%	73%	64%	64%	59%	67%	64%
72.2%	75%	66%	80%	75%	70%	67%
74.3%	77%	70%	72%	69%	79%	79%
79.0%	85%	76%	85%	90%	59%	79%
53.5%	55%	73%	48%	67%	39%	39%
72.3%	67%	59%	80%	82%	73%	73%
74.2%	79%	69%	73%	79%	63%	82%
70.3%	83%	94%	54%	70%	54%	67%
53.5%	56%	69%	31%	52%	61%	52%
41.3%	42%	63%	36%	34%	34%	39%
78.7%	73%	73%	80%	80%	80%	86%
71.0%	70%	64%	71%	80%	63%	78%
66.0%	55%	49%	81%	74%	66%	71%
52.0%	68%	48%	53%	53%	36%	54%
73.5%	64%	81%	64%	76%	76%	80%
53.8%	52%	70%	55%	72%	37%	37%
68.0%	64%	67%	71%	68%	65%	73%
56.2%	63%	61%	52%	61%	38%	62%
71.8%	79%	60%	58%	82%	78%	74%
69.2%	79%		72%	56%	68%	71%
65.7%	69%	72%	57%	64%	71%	61%
61.0%	50%	49%	74%	69%	62%	62%
55.2%	56%	72%	56%	51%	45%	51%
73.2%	72%	57%	72%	77%	84%	77%
77.7%	83%	55%	81%	87%	80%	80%
55.5%	67%	31%	69%	53%	51%	62%
62.7%	67%	37%	71%	63%	70%	68%
70.0%	56%	65%	76%	83%	72%	68%
87.3%	97%	86%	83%	94%	84%	80%
55.0%	48%	48%	65%	65%	37%	67%
90.5%	100%	89%	94%	89%	82%	89%
76.2%	81%	68%	74%	78%	78%	78%
59.2%	66%	62%	41%	68%	56%	62%
80.3%	88%	73%	77%	88%	73%	83%