	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 68.4%	2nd 67.5%	6th 62.3%	3rd 66.2%	5th 63.0%	4th 64.5%
28.7%	26%	35%	29%	28%	28%	26%
72.2%	78%	50%	77%	76%	72%	80%
77.8%	75%	79%	71%	84%	76%	82%
70.8%	68%	72%	68%	72%	71%	74%
63.2%	68%	72%	71%	66%	44%	58%
61.7%	73%	59%	70%	70%	42%	56%
52.0%	56%	46%	49%	54%	54%	53%
76.5%	82%	84%	61%	79%	74%	79%
60.2%	48%	65%	69%	52%	79%	48%
72.8%	83%	76%	73%	67%	66%	72%
79.2%	72%	80%	87%	80%	78%	78%
76.0%	79%	77%	68%	77%	78%	77%
64.7%	72%	63%	65%	65%	58%	65%
62.0%	63%	58%	59%	71%	52%	69%
73.0%	70%	81%	78%	60%	89%	60%
93.5%	99%	91%	94%	93%	90%	94%
72.2%	73%	72%	78%	67%	70%	73%
50.8%	65%	45%	50%	50%	50%	45%
60.0%	62%	69%	60%	60%	59%	50%
46.8%	57%	55%	34%	58%	23%	54%
63.0%	68%	54%	63%	63%	67%	63%
60.3%	63%	64%	56%	55%	61%	63%
60.3%	70%	66%	61%	55%	45%	65%
83.3%	87%	83%	79%	84%	81%	86%
21.8%	16%	26%	28%	16%	21%	24%
77.3%	85%	69%	83%	72%	76%	79%
80.2%	89%	76%	70%	78%	84%	84%
60.2%	75%	53%	55%	64%	53%	61%
78.8%	79%	78%	64%	85%	83%	84%
63.8%	74%	76%	42%	72%	73%	46%
51.8%	52%	55%	51%	59%	39%	55%
54.8%	62%	46%	57%	57%	49%	58%
77.5%	82%	82%	81%	79%	70%	71%
56.0%	57%	54%	67%	52%	46%	60%
74.8%	78%	74%	70%	76%	71%	80%
60.2%	60%	62%	47%	65%	70%	57%
56.3%	51%	35%	53%	63%	73%	63%
58.0%	53%	60%	54%	65%	56%	60%
71.8%	73%	65%	72%	80%	69%	72%
51.3%	56%	64%	35%	50%	52%	51%
64.3%	72%	62%	53%	65%	69%	65%
83.5%	87%	84%	78%	92%	77%	83%
76.2%	82%	77%	79%	80%	63%	76%
64.0%	63%	66%	62%	65%	63%	65%
64.3%	70%	64%	67%	69%	54%	62%
56.5%	63%	69%	53%	59%	46%	49%
76.8%	80%	76%	74%	78%	72%	81%
66.3%	64%	66%	65%	69%	66%	68%
55.7%	52%	51%	67%	58%	46%	60%
57.7%	69%	66%	39%	59%	60%	53%
72.2%	79%	79%	61%	74%	69%	71%
77.8%	85%	91%	53%	80%	86%	72%
61.3%	66%	67%	50%	63%	61%	61%
69.0%	72%	75%	64%	74%	59%	70%
82.5%	80%	77%	93%	65%	95%	85%
62.8%	74%	73%	52%	74%	50%	54%
53.5%	61%	61%	56%	59%	44%	40%
64.5%	65%	78%	51%	74%	66%	53%
69.5%	68%	74%	65%	70%	67%	73%
50.7%	51%	55%	45%	51%	51%	51%
59.7%	72%	70%	45%	49%	68%	54%
69.5%	64%	62%	80%	62%	76%	73%
58.8%	55%	63%	63%	59%	58%	55%
65.3%	69%	67%	69%	56%	73%	58%
46.7%	45%	50%	39%	53%	44%	49%
67.3%	66%	68%	71%	67%	61%	71%
88.2%	95%	91%	79%	84%	96%	84%
70.2%	74%	65%	69%	74%	61%	78%
69.0%	64%	72%	79%	68%	67%	64%
69.8%	91%	34%	80%	79%	70%	65%
64.2%	68%	67%	69%	59%	59%	63%
47.5%	48%	64%	39%	59%	30%	45%
52.2%	53%	60%	35%	50%	63%	52%
68.8%	64%	72%	75%	64%	69%	69%
57.0%	60%	64%	55%	66%	27%	70%
50.0%	53%	46%	46%	48%	53%	54%
83.0%	81%	90%	85%	80%	79%	83%
39.2%	27%	45%	46%	34%	37%	46%
65.0%	76%	63%	60%	67%	58%	66%
48.7%	61%	73%	10%	60%	44%	44%
62.7%	69%	100%	49%	51%	73%	34%
88.5%	98%	86%	75%	93%	96%	83%
65.8%	76%	72%	34%	73%	67%	73%
71.2%	67%	69%	89%	72%	57%	73%
74.8%	79%	83%	72%	79%	66%	70%
65.0%	72%	76%	45%	66%	70%	61%
67.0%	64%	70%	72%	60%	63%	73%
78.5%	75%	82%	72%	83%	78%	81%
73.8%	76%	83%	86%	63%	62%	73%
83.8%	84%	88%	81%	81%	88%	81%
68.2%	74%	68%	70%	71%	65%	61%