	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 69.1%	1st 70.2%	6th 57.9%	3rd 67.1%	5th 61.5%	4th 65.4%
71.2%	83%	77%	41%	80%	77%	69%
83.7%	82%	78%	84%	84%	88%	86%
80.3%	75%	82%	87%	81%	82%	75%
31.7%	36%	36%	33%	32%	15%	38%
83.0%	81%	84%	87%	82%	80%	84%
68.8%	81%	81%	52%	66%	64%	69%
64.5%	64%	75%	62%	62%	66%	58%
66.0%	82%	85%	36%	68%	59%	66%
84.5%	86%	100%	68%	89%	75%	89%
38.3%	41%	47%	44%	37%	14%	47%
83.5%	84%	71%	87%	82%	89%	88%
29.8%	37%	36%	25%	36%	9%	36%
73.8%	88%	73%	59%	76%	71%	76%
88.3%	91%	89%	87%	92%	87%	84%
68.0%	65%	72%	54%	57%	90%	70%
57.7%	63%	66%	33%	62%	62%	60%
52.7%	61%	65%	38%	60%	46%	46%
56.7%	65%	76%	36%	56%	61%	46%
63.7%	73%	49%	61%	72%	60%	67%
61.8%	56%	70%	62%	70%	58%	55%
72.2%	86%	78%	56%	73%	68%	72%
70.0%	76%	81%	53%	72%	66%	72%
73.8%	77%	78%	76%	83%	45%	84%
69.8%	79%	74%	59%	77%	59%	71%
58.8%	61%	62%	57%	59%	57%	57%
68.2%	63%	65%	69%	72%	64%	76%
54.7%	62%	64%	37%	50%	68%	47%
48.2%	54%	71%	33%	48%	49%	34%
35.3%	32%	39%	25%	50%	20%	46%
57.5%	54%	57%	58%	69%	54%	53%
73.3%	80%	81%	58%	71%	78%	72%
73.8%	79%	73%	67%	73%	72%	79%
55.2%	53%	53%	63%	58%	51%	53%
72.3%	77%	78%	73%	78%	64%	64%
52.8%	64%	32%	65%	52%	32%	72%
69.3%	77%	90%	54%	67%	67%	61%
72.2%	72%	72%	72%	66%	81%	70%
86.0%	85%	84%	84%	89%	86%	88%
47.7%	58%	56%	36%	46%	45%	45%
92.0%	89%	95%	99%	89%	91%	89%
69.3%	70%	100%	53%	63%	63%	67%
53.0%	51%	52%	43%	54%	62%	56%
69.5%	77%	71%	63%	82%	50%	74%