	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 66.0%	3rd 63.6%	6th 58.5%	1st 66.2%	5th 58.7%	4th 61.8%
58.2%	66%	26%	51%	73%	60%	73%
58.0%	66%	65%	49%	65%	43%	60%
48.8%	61%	66%	36%	47%	36%	47%
100.0%	100%	100%	100%	100%	100%	100%
63.2%	68%	82%	73%	68%	39%	49%
54.0%	50%	63%	56%	50%	69%	36%
76.3%	83%	78%	78%	78%	78%	63%
42.0%	38%	54%	42%	42%	36%	40%
60.0%	59%	71%	66%	72%	39%	53%
61.2%	64%	63%	50%	69%	68%	53%
61.5%	74%	75%	61%	61%	53%	45%
62.7%	69%	50%	72%	72%	51%	62%
70.8%	76%	77%	65%	71%	60%	76%
100.0%	100%	100%	100%	100%	100%	100%
47.7%	45%	41%	50%	52%	52%	46%
47.2%	54%	38%	41%	54%	48%	48%
83.2%	78%	82%	68%	89%	100%	82%
62.5%	52%	92%	38%	68%	57%	68%
54.3%	57%	43%	56%	62%	43%	65%
68.2%	75%	63%	61%	75%	75%	60%
37.7%	42%	25%	54%	43%	16%	46%
60.0%	83%	40%	63%	66%	34%	74%
72.2%	81%	77%	77%	69%	60%	69%
68.0%	70%	56%	68%	70%	74%	70%
74.0%	78%	85%	72%	75%	56%	78%
54.2%	50%	62%	62%	62%	41%	48%
52.3%	61%	40%	63%	53%	60%	37%
68.8%	73%	52%	79%	73%	57%	79%
72.7%	84%	77%	10%	84%	86%	95%
58.3%	78%	78%	40%	54%	50%	50%
44.5%	51%	13%	44%	59%	50%	50%
61.0%	61%	62%	61%	68%	61%	53%
61.3%	70%	69%	54%	61%	55%	59%
57.5%	55%	78%	51%	54%	53%	54%
57.2%	61%	59%	55%	46%	61%	61%
82.7%	82%	89%	63%	91%	89%	82%
63.3%	61%	66%	67%	66%	54%	66%
49.3%	56%	69%	40%	54%	35%	42%
43.3%	46%	36%	36%	61%	36%	45%
62.5%	70%	63%	50%	70%	61%	61%
46.8%	40%	58%	45%	43%	47%	48%
57.3%	57%	57%	57%	58%	53%	62%
63.8%	74%	61%	34%	73%	75%	66%
83.3%	84%	90%	82%	72%	90%	82%
59.0%	61%	47%	61%	71%	54%	60%
83.5%	72%	88%	91%	82%	86%	82%