	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 66.6%	1st 66.6%	4th 63.9%	3rd 65.1%	6th 61.2%	5th 62.3%
77.5%	77%	64%	85%	88%	63%	88%
63.2%	60%	37%	82%	70%	63%	67%
48.3%	50%	44%	41%	54%	47%	54%
59.5%	57%	74%	55%	62%	70%	39%
70.8%	70%	80%	71%	70%	64%	70%
80.8%	82%	64%	82%	81%	88%	88%
65.3%	60%	75%	62%	62%	68%	65%
67.7%	61%	82%	59%	61%	82%	61%
83.5%	82%	91%	69%	91%	89%	79%
70.0%	70%	70%	70%	70%	70%	70%
49.7%	54%	32%	71%	48%	54%	39%
72.3%	78%	68%	70%	74%	70%	74%
79.8%	76%	91%	81%	75%	56%	100%
67.7%	74%	75%	69%	74%	56%	58%
76.5%	89%	71%	75%	84%	71%	69%
68.5%	68%	68%	66%	76%	57%	76%
62.7%	76%	76%	56%	60%	48%	60%
53.2%	54%	70%	32%	49%	60%	54%
36.3%	20%	78%	22%	37%	22%	39%
52.2%	67%	60%	52%	56%	39%	39%
62.8%	66%	58%	62%	66%	65%	60%
75.8%	73%	58%	88%	87%	76%	73%
61.0%	62%	62%	64%	58%	55%	65%
72.7%	75%	74%	78%	75%	60%	74%
68.8%	68%	75%	65%	70%	67%	68%
72.5%	66%	68%	89%	75%	63%	74%
51.0%	59%	59%	48%	48%	38%	54%
34.3%	41%	66%	19%	34%	27%	19%
68.8%	100%	55%	63%	66%	63%	66%
69.3%	70%	73%	78%	68%	64%	63%
50.8%	50%	48%	48%	55%	50%	54%
83.3%	81%	88%	92%	77%	85%	77%
48.3%	50%	44%	41%	54%	47%	54%
43.5%	52%	54%	38%	39%	39%	39%
56.3%	65%	41%	68%	47%	70%	47%
53.8%	61%	55%	51%	59%	44%	53%
70.5%	76%	87%	62%	66%	70%	62%
64.3%	65%	69%	73%	65%	54%	60%
51.2%	53%	61%	50%	53%	53%	37%
91.2%	89%	96%	100%	85%	92%	85%
59.3%	63%	63%	55%	61%	63%	51%
80.2%	83%	83%	83%	75%	81%	76%
68.7%	69%	58%	64%	75%	68%	78%