	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 67.3%	5th 63.7%	3rd 64.9%	2nd 67.2%	6th 63.3%	4th 64.4%
22.8%	16%	73%	8%	16%	16%	8%
73.7%	84%	29%	80%	83%	83%	83%
67.5%	64%	80%	62%	66%	70%	63%
63.3%	65%	52%	71%	69%	54%	69%
65.2%	65%	78%	71%	69%	54%	54%
67.7%	78%	48%	80%	77%	65%	58%
53.5%	64%	34%	52%	62%	56%	53%
73.3%	76%	92%	61%	81%	69%	61%
83.3%	73%	93%	93%	74%	93%	74%
63.8%	59%	80%	64%	61%	63%	56%
67.5%	61%	67%	72%	65%	80%	60%
72.3%	78%	76%	76%	74%	72%	58%
76.2%	76%	76%	76%	77%	63%	89%
62.2%	58%	71%	62%	58%	61%	63%
63.3%	71%	93%	63%	45%	63%	45%
93.3%	97%	93%	80%	100%	97%	93%
62.2%	68%	40%	73%	65%	65%	62%
60.2%	71%	51%	62%	61%	58%	58%
61.7%	63%	58%	65%	77%	50%	57%
50.3%	62%	55%	46%	44%	51%	44%
64.2%	61%	66%	67%	60%	60%	71%
68.8%	78%	60%	60%	78%	84%	53%
62.2%	70%	72%	58%	63%	51%	59%
42.2%	46%	31%	42%	46%	42%	46%
18.7%	12%	33%	18%	12%	25%	12%
58.7%	67%	41%	70%	52%	62%	60%
67.5%	68%	60%	71%	62%	73%	71%
71.2%	76%	72%	77%	73%	52%	77%
54.0%	49%	55%	64%	52%	52%	52%
62.7%	58%	58%	50%	72%	58%	80%
83.7%	74%	71%	93%	71%	100%	93%
65.8%	77%	43%	68%	76%	67%	64%
85.0%	100%	68%	89%	100%	76%	77%
58.7%	64%	69%	58%	58%	54%	49%
50.0%	55%	39%	48%	55%	46%	57%
58.0%	62%	60%	52%	58%	58%	58%
64.3%	64%	51%	73%	74%	62%	62%
66.7%	59%	63%	61%	77%	68%	72%
72.5%	74%	74%	70%	69%	70%	78%
45.3%	58%	59%	33%	40%	40%	42%
70.3%	73%	71%	59%	69%	73%	77%
69.0%	72%	52%	76%	72%	71%	71%
76.0%	72%	81%	91%	82%	51%	79%
62.5%	70%	55%	65%	71%	51%	63%
75.3%	76%	72%	79%	80%	72%	73%
70.0%	71%	93%	54%	93%	54%	55%
64.7%	63%	56%	57%	68%	72%	72%
64.7%	61%	49%	70%	68%	70%	70%
67.5%	83%	71%	49%	71%	74%	57%
64.8%	76%	59%	50%	76%	68%	60%
61.8%	71%	58%	53%	65%	66%	58%
65.7%	78%	80%	52%	67%	70%	47%
68.2%	71%	54%	78%	68%	69%	69%
77.3%	81%	91%	73%	73%	73%	73%
71.0%	73%	60%	69%	73%	77%	74%
66.7%	75%	47%	57%	89%	61%	71%
71.0%	80%	77%	69%	70%	62%	68%
51.3%	61%	71%	45%	57%	35%	39%
84.8%	90%	79%	90%	84%	77%	89%
86.5%	88%	93%	66%	87%	92%	93%
57.8%	61%	53%	53%	60%	60%	60%
73.3%	76%	66%	77%	66%	69%	86%
56.2%	56%	27%	68%	57%	63%	66%
47.3%	47%	32%	45%	51%	51%	58%
81.3%	90%	66%	83%	83%	83%	83%
54.2%	62%	21%	69%	55%	59%	59%
73.0%	73%	63%	77%	73%	73%	79%
67.3%	71%	51%	65%	69%	71%	77%
55.3%	64%	58%	51%	62%	46%	51%
70.0%	67%	47%	81%	79%	57%	89%
57.0%	57%	59%	48%	61%	53%	64%
70.0%	63%	67%	77%	69%	62%	82%
33.5%	33%	64%	31%	33%	20%	20%
57.3%	63%	26%	69%	54%	63%	69%
93.7%	62%	100%	100%	100%	100%	100%
70.5%	70%	66%	77%	72%	66%	72%
80.0%	80%	80%	80%	80%	80%	80%
44.5%	32%	52%	61%	32%	49%	41%
73.8%	68%	76%	71%	73%	77%	78%
66.2%	75%	90%	54%	77%	47%	54%
73.3%	67%	100%	64%	100%	58%	51%
87.7%	88%	100%	90%	81%	78%	89%
56.7%	61%	56%	53%	61%	61%	48%
50.0%	54%	64%	44%	40%	54%	44%
64.7%	68%	54%	69%	71%	61%	65%
61.5%	69%	68%	46%	69%	63%	54%
66.7%	69%	84%	61%	61%	57%	68%
51.2%	46%	36%	66%	53%	60%	46%
66.0%	68%	51%	79%	66%	66%	66%
87.5%	86%	92%	85%	86%	84%	92%
64.3%	68%	71%	68%	63%	46%	70%