	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 73.1%	1st 73.5%	6th 67.1%	3rd 72.5%	5th 68.1%	4th 70.4%
29.8%	28%	34%	25%	26%	33%	33%
74.0%	76%	75%	71%	76%	76%	70%
83.8%	81%	84%	85%	87%	88%	78%
71.7%	76%	73%	59%	76%	71%	75%
79.3%	79%	89%	89%	82%	60%	77%
61.4%		63%	80%	79%	43%	42%
67.0%	72%	61%	62%	71%	67%	69%
65.6%		60%	63%	71%	67%	67%
67.7%	72%	87%	10%	74%	91%	72%
69.3%	77%	76%	69%	62%	57%	75%
75.7%	74%	85%	67%	75%	75%	78%
73.2%	82%	75%	63%	69%	85%	65%
61.2%		64%	64%	58%	62%	58%
82.5%	85%	79%	82%	86%	71%	92%
34.8%	37%	35%	34%	22%	55%	26%
74.3%	80%	79%	58%	77%	74%	78%
87.7%	89%	89%	86%	85%	88%	89%
49.5%	52%	49%	54%	50%	50%	42%
75.0%	75%	77%	74%	81%	68%	75%
42.2%	55%	45%	30%	53%	23%	47%
75.2%		70%	81%	75%	76%	74%
75.0%	72%	80%	59%	81%	84%	74%
81.8%	92%	82%	80%	72%	78%	87%
80.2%	78%	84%	84%	79%	72%	84%
45.5%	39%	49%	41%	41%	46%	57%
69.0%	67%	79%	61%	80%	58%	69%
75.7%	75%	74%	77%	74%	77%	77%
66.8%	61%	87%	60%	68%	60%	65%
72.5%	73%	76%	66%	76%	72%	72%
66.3%	79%	77%	38%	74%	78%	52%
59.3%	56%	64%	55%	64%	55%	62%
75.8%	81%	69%	76%	74%	78%	77%
66.4%		73%	73%	66%	62%	58%
70.2%	74%	79%	79%	68%	51%	70%
75.0%	75%	74%	81%	78%	64%	78%
66.3%	70%	68%	61%	68%	67%	64%
68.5%	68%	64%	67%	70%	71%	71%
73.2%	66%	74%	76%	78%	67%	78%
77.8%		84%	77%	83%	75%	70%
64.5%	72%	67%	46%	71%	68%	63%
58.2%		52%	44%	61%	73%	61%
71.3%	77%	71%	62%	71%	76%	71%
64.8%	68%	71%	67%	75%	46%	62%
71.3%	74%	80%	59%	73%	70%	72%
74.3%	78%	76%	84%	77%	61%	70%
53.8%		68%	42%	59%	41%	59%
79.5%	76%	72%	82%	86%	81%	80%
73.0%	67%	70%	79%	70%	78%	74%
64.7%	70%	68%	76%	64%	46%	64%
77.0%	82%	80%	69%	79%	73%	79%
72.8%	79%	77%	64%	75%	71%	71%
75.2%	81%	80%	80%	69%	67%	74%
75.7%	80%	80%	72%	76%	73%	73%
68.0%	70%	69%	69%	71%	66%	63%
72.3%	68%	69%	74%	72%	75%	76%
57.8%	62%	79%	35%	66%	44%	61%
66.5%	74%	64%	71%	73%	59%	58%
73.8%	81%	64%	76%	76%	74%	72%
77.8%	82%	72%	84%	79%	74%	76%
84.8%	89%	83%	74%	89%	87%	87%
59.3%	65%	64%	45%	60%	67%	55%
76.3%	76%	76%	77%	74%	77%	78%
74.6%		77%	69%	76%	72%	79%
78.3%	71%	80%	81%	84%	71%	83%
71.3%	65%	72%	72%	72%	72%	75%
76.2%	76%	78%	80%	78%	75%	70%
71.0%	73%	68%	84%	66%	69%	66%
84.0%	84%		85%	92%	70%	89%
88.2%		94%	93%	93%	84%	77%
82.4%		89%	91%	74%	81%	77%
86.5%	95%	93%	91%	87%	66%	87%
57.5%	64%	58%	42%	69%	48%	64%
57.5%	60%	61%	44%	61%	58%	61%
73.4%		74%	64%	73%	78%	78%
51.0%	45%	55%	47%	58%	44%	57%
84.5%	82%	81%	83%	86%	87%	88%
84.5%	89%	82%	76%	86%	87%	87%
69.8%	63%	71%	64%	68%	75%	78%
84.0%	85%	87%	84%	82%	85%	81%
46.2%	61%	66%	10%	59%	37%	44%
59.3%	69%	100%	48%	51%	44%	44%
68.5%	75%	77%	55%	69%	72%	63%
80.5%	83%	85%	65%	85%	84%	81%
80.8%	87%	81%	92%	82%	64%	79%
80.3%	77%	79%	80%	79%	79%	88%
72.0%	74%	74%	59%	79%	73%	73%
68.7%	72%	80%	62%	62%	63%	73%
86.2%	84%	76%	90%	91%	91%	85%
86.3%	96%	86%	88%	87%	83%	78%
84.8%	87%	80%	84%	87%	87%	84%
68.2%	70%	76%	73%	67%	55%	68%