	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 64.6%	4th 62.5%	3rd 63.1%	1st 65.3%	6th 58.7%	5th 61.2%
62.0%	70%	70%	63%	63%	59%	47%
53.3%	66%	54%	48%	57%	49%	46%
62.5%	60%	78%	71%	56%	48%	62%
53.8%	59%	64%	52%	52%	43%	53%
65.5%	62%	63%	74%	76%	42%	76%
70.3%	82%	41%	84%	82%	70%	63%
57.5%	58%	62%	55%	58%	56%	56%
58.8%	66%	100%	50%	44%	56%	37%
51.5%	54%	66%	46%	52%	40%	51%
59.7%	66%	62%	51%	66%	59%	54%
84.3%	89%	78%	71%	91%	91%	86%
54.7%	57%	25%	57%	69%	59%	61%
56.8%	61%	79%	56%	63%	38%	44%
54.8%	53%	56%	61%	59%	38%	62%
52.8%	49%	39%	60%	59%	59%	51%
65.2%	76%	77%	63%	74%	46%	55%
61.3%	66%	55%	57%	75%	60%	55%
67.0%	75%	67%	68%	74%	50%	68%
69.2%	75%	72%	77%	74%	58%	59%
64.0%	70%	65%	66%	63%	62%	58%
72.2%	72%	64%	76%	79%	75%	67%
59.5%	61%	52%	70%	59%	45%	70%
38.0%	50%	50%	32%	26%	44%	26%
70.3%	76%	52%	71%	76%	74%	73%
54.5%	55%	42%	65%	59%	39%	67%
65.3%	67%	51%	79%	79%	45%	71%
86.5%	86%	89%	95%	79%	79%	91%
70.3%	76%	70%	65%	76%	73%	62%
66.2%	69%	81%	47%	81%	57%	62%
79.0%	58%	86%	86%	72%	86%	86%
42.3%	35%	71%	21%	35%	46%	46%
60.0%	59%	60%	62%	57%	61%	61%
52.8%	56%	55%	45%	56%	52%	53%
62.3%	66%	51%	63%	59%	63%	72%
73.7%	71%	86%	79%	71%	71%	64%
69.8%	73%	81%	67%	68%	60%	70%
71.5%	67%	61%	81%	76%	67%	77%
53.3%	55%	58%	62%	52%	61%	32%
68.5%	70%	50%	60%	79%	76%	76%
66.0%	66%	70%	64%	70%	71%	55%
58.7%	60%	51%	61%	60%	60%	60%
59.3%	50%	56%	69%	66%	54%	61%
65.8%	66%	60%	75%	66%	66%	62%
55.2%	66%	38%	67%	52%	54%	54%
88.3%	87%	91%	68%	100%	91%	93%
68.2%	63%	75%	63%	72%	86%	50%
51.3%	62%	59%	46%	59%	46%	36%
65.8%	67%	76%	60%	66%	59%	67%
82.8%	73%	78%	82%	86%	86%	92%
66.8%	61%	84%	80%	56%	44%	76%
38.2%	48%	25%	41%	51%	23%	41%
65.2%	69%	62%	62%	59%	70%	69%
46.2%	47%	56%	47%	36%	50%	41%
59.3%	67%	13%	66%	79%	55%	76%