	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	1st 66.1%	4th 63.1%	6th 61.2%	2nd 64.9%	5th 62.9%	3rd 64.0%
38.7%	22%	62%	32%	40%	36%	40%
65.7%	66%	64%	66%	68%	65%	65%
72.2%	76%	59%	70%	76%	75%	77%
54.2%	59%	52%	38%	62%	60%	54%
73.5%	78%	80%	70%	74%	57%	82%
62.7%	74%	46%	80%	65%	60%	51%
50.7%	53%	37%	51%	58%	57%	48%
58.5%	59%	63%	49%	63%	66%	51%
62.7%	59%	85%	10%	61%	100%	61%
68.2%	75%	77%	77%	57%	57%	66%
58.2%	53%	61%	51%	58%	74%	52%
67.2%	71%	76%	65%	53%	82%	56%
81.0%	86%	83%	100%	85%	57%	75%
80.8%	88%	71%	87%	84%	81%	74%
64.5%	78%	91%	64%	48%	57%	49%
54.8%	61%	70%	10%	70%	59%	59%
56.0%	54%	50%	54%	43%	64%	71%
65.7%	77%	60%	70%	60%	66%	61%
60.3%	63%	52%	64%	65%	61%	57%
72.0%	79%	75%	68%	70%	70%	70%
73.7%	64%	72%	76%	69%	80%	81%
53.7%	67%	44%	41%	59%	57%	54%
55.8%	57%	70%	51%	49%	60%	48%
72.7%	80%	51%	84%	73%	74%	74%
46.7%	29%	52%	53%	45%	57%	44%
58.3%	64%	52%	55%	52%	59%	68%
68.0%	76%	61%	51%	81%	62%	77%
72.5%	71%	75%	53%	77%	77%	82%
69.8%	70%	67%	69%	66%	74%	73%
58.3%	58%	100%	30%	44%	63%	55%
68.8%	73%	69%	59%	77%	77%	58%
59.0%	70%	40%	62%	62%	62%	58%
78.3%	74%	80%	74%	85%	77%	80%
73.7%	76%	75%	75%	75%	59%	82%
40.2%	44%	44%	44%	37%	28%	44%
51.2%	56%	46%	56%	52%	42%	55%
52.7%	58%	35%	56%	56%	57%	54%
61.0%	73%	52%	71%	55%	54%	61%
76.2%	84%	84%	79%	75%	63%	72%
52.5%	58%	70%	27%	52%	54%	54%
63.8%	63%	63%	47%	65%	74%	71%
59.8%	53%	32%	67%	67%	64%	76%
75.8%	76%	77%	79%	76%	70%	77%
53.5%	61%	69%	34%	61%	49%	47%
60.3%	59%	57%	70%	74%	37%	65%
61.5%	58%	81%	43%	77%	54%	56%
70.3%	75%	66%	77%	75%	58%	71%
57.0%	58%	53%	58%	58%	61%	54%
74.7%	79%	75%	74%	72%	64%	84%
62.0%	66%	38%	72%	68%	53%	75%
60.0%	59%	70%	45%	66%	61%	59%
75.3%	80%	76%	81%	75%	65%	75%
65.0%	64%	42%	69%	72%	72%	71%
56.0%	55%	52%	56%	59%	58%	56%
72.0%	76%	62%	75%	73%	75%	71%
63.0%	70%	66%	50%	76%	45%	71%
77.2%	76%	72%	85%	77%	69%	84%
64.2%	71%	55%	56%	69%	81%	53%
53.7%	69%	48%	51%	52%	59%	43%
53.3%	62%	52%	41%	63%	43%	59%
55.0%	70%	80%	30%	46%	64%	40%
62.7%	54%	63%	62%	66%	66%	65%
73.0%	69%	41%	82%	75%	87%	84%
72.3%	81%	54%	78%	67%	77%	77%
67.5%	65%	49%	75%	69%	81%	66%
58.8%	74%	19%	72%	59%	68%	61%
68.2%	62%	68%	77%	68%	71%	63%
70.0%	75%	79%	62%	62%	76%	66%
64.3%	67%	54%	66%	76%	70%	53%
55.3%	0%	38%	73%	74%	64%	83%
65.3%	72%	58%	73%	77%	33%	79%
70.7%	70%	66%	67%	70%	66%	85%
32.3%	30%	64%	23%	35%	25%	17%
49.7%	53%	41%	44%	59%	47%	54%
80.8%	97%	77%		77%	77%	76%
71.7%	71%	67%	68%	71%	76%	77%
70.0%	70%	70%	70%	70%	70%	70%
77.2%	64%	86%	81%	74%	85%	73%
68.7%	72%	74%	62%	62%	72%	70%
65.5%	85%	89%	50%	76%	35%	58%
66.2%	72%	100%	63%	44%	59%	59%
66.8%	70%	79%	67%	63%	60%	62%
44.7%	55%	49%	27%	48%	46%	43%
52.2%	55%	51%	52%	55%	45%	55%
66.2%	69%	56%	64%	72%	63%	73%
53.8%	63%	41%	48%	57%	59%	55%
63.7%	69%	64%	67%	54%	63%	65%
72.2%	70%	69%	73%	70%	74%	77%
81.8%	92%	77%	91%	85%	71%	75%
76.7%	71%	76%	92%	70%	80%	71%
67.0%	69%	84%	73%	75%	38%	63%