	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	3rd 65.8%	5th 61.2%	4th 63.4%	1st 66.1%	6th 60.7%	2nd 65.9%
54.3%	64%	76%	23%	55%	53%	55%
59.5%	66%	75%	44%	59%	54%	59%
77.3%	84%	83%	68%	77%	77%	75%
52.7%	52%	52%	53%	51%	58%	50%
52.0%	57%	59%	54%	57%	36%	49%
69.5%	78%	40%	77%	71%	70%	81%
53.0%	67%	63%	46%	52%	43%	47%
53.7%	56%	45%	52%	51%	60%	58%
67.5%	68%	68%	64%	68%	66%	71%
65.7%	58%	62%	73%	66%	69%	66%
78.5%	78%	62%	81%	80%	85%	85%
74.5%	83%	68%	79%	82%	55%	80%
76.3%	79%	71%	77%	77%	76%	78%
53.8%	75%	41%	46%	62%	42%	57%
52.5%	45%	22%	62%	57%	58%	71%
58.8%	60%	58%	59%	58%	57%	61%
72.2%	72%	75%	68%	72%	69%	77%
69.7%	73%	64%	64%	80%	63%	74%
75.0%	79%	71%	77%	82%	67%	74%
77.0%	89%	87%	54%	81%	66%	85%
75.2%	78%	69%	78%	75%	76%	75%
78.7%	79%	80%	79%	79%	76%	79%
53.2%	59%	38%	61%	49%	56%	56%
17.8%	17%	26%	17%	16%	18%	13%
52.0%	60%	40%	61%	45%	58%	48%
76.8%	79%	76%	80%	81%	67%	78%
80.5%	85%	77%	81%	85%	76%	79%
71.2%	70%	73%	61%	76%	74%	73%
74.3%	83%	69%	79%	75%	67%	73%
72.8%	74%	68%	63%	78%	80%	74%
67.2%	74%	59%	73%	69%	64%	64%
52.5%	57%	56%	42%	68%	44%	48%
58.7%	64%	66%	50%	62%	46%	64%
31.8%	25%	53%	32%	28%	25%	28%
58.0%	56%	58%	59%	55%	62%	58%
50.7%	48%	46%	52%	49%	52%	57%
72.5%	70%	74%	67%	74%	76%	74%
56.5%	42%	51%	64%	54%	58%	70%
73.0%	83%	45%	80%	75%	76%	79%
25.3%	15%	26%	30%	22%	22%	37%
64.0%	67%	63%	66%	71%	55%	62%
53.5%	69%	35%	71%	48%	50%	48%
52.0%	54%	47%	47%	58%	53%	53%
63.2%	59%	61%	57%	54%	82%	66%
76.0%	78%	85%	86%	73%	74%	60%
67.7%	80%	81%	57%	74%	50%	64%
67.3%	72%	74%	67%	59%	74%	58%
90.7%	98%	88%	81%	96%	89%	92%
79.0%	76%	74%	88%	82%	77%	77%
65.0%	74%	63%	67%	62%	59%	65%
60.2%	64%	66%	63%	57%	49%	62%
47.5%	48%	44%	41%	38%	53%	61%
71.3%	82%	71%	57%	75%	66%	77%
46.0%	45%	52%	40%	49%	45%	45%
75.5%	77%	74%	79%	74%	70%	79%
81.8%	91%	48%	87%	88%	85%	92%
50.7%	52%	63%	47%	61%	42%	39%
62.2%	69%	48%	69%	66%	53%	68%
42.3%	40%	66%	34%	40%	34%	40%
59.2%	62%	43%	69%	63%	67%	51%
64.5%	67%	56%	70%	56%	69%	69%
61.5%	64%	63%	43%	63%	66%	70%
71.7%	73%	56%	60%	71%	87%	83%
55.8%	58%	43%	63%	59%	58%	54%
76.0%	84%	23%	93%	85%	87%	84%
72.7%	76%	62%	79%	71%	76%	72%
71.7%	74%	92%	58%	65%	73%	68%
72.8%	79%	69%	83%	93%	54%	59%
45.2%	30%	47%	43%	52%	50%	49%
65.7%	77%	60%	50%	81%	51%	75%
66.3%	72%	38%	73%	70%	64%	81%
77.0%	80%	71%	77%	78%	78%	78%
69.5%	70%	65%	67%	69%	72%	74%
56.8%	49%	77%	48%	50%	46%	71%
64.7%	65%	46%	68%	69%	70%	70%
74.5%	79%	76%	65%	75%	75%	77%
54.7%	55%	53%	57%	53%	50%	60%
72.0%	71%	67%	59%	76%	78%	81%
80.3%	82%	54%	86%	84%	88%	88%
62.2%	65%	67%	66%	61%	57%	57%
77.5%	82%	76%	70%	87%	60%	90%
77.7%	81%	79%	82%	93%	52%	79%
77.7%	80%	54%	87%	80%	84%	81%
88.0%	89%	80%	85%	91%	96%	87%
74.2%	81%	74%	71%	74%	67%	78%
77.3%	76%	77%	80%	72%	77%	82%
48.2%	44%	55%	54%	51%	41%	44%
64.3%	62%	64%	71%	66%	56%	67%
72.5%	76%	79%	88%	82%	46%	64%
65.8%	70%	77%	77%	69%	38%	64%
42.5%	37%	46%	42%	43%	41%	46%
32.7%	32%	31%	20%	58%	28%	27%
56.7%	75%	22%	57%	58%	53%	75%
63.5%	59%	60%	73%	68%	55%	66%
25.8%	25%	27%	36%	22%	27%	18%
61.7%	59%	67%	61%	57%	63%	63%
72.3%	66%	61%	76%	74%	74%	83%
68.7%	76%	56%	65%	75%	72%	68%
62.0%	59%	87%	38%	71%	46%	71%
58.0%	62%	53%	61%	70%	51%	51%
49.2%	51%	34%	57%	54%	46%	53%
77.5%	83%	78%	73%	86%	65%	80%
59.8%	57%	63%	56%	56%	63%	64%
79.8%	68%	85%	76%	82%	84%	84%
75.8%	81%	75%	78%	80%	65%	76%
59.3%	46%	54%	59%	66%	64%	67%
74.7%	77%	80%	76%	75%	67%	73%
41.0%	42%	57%	28%	46%	28%	45%
63.3%	66%	73%	62%	67%	41%	71%
65.7%	63%	80%	67%	66%	59%	59%
74.2%	73%	75%	76%	74%	71%	76%
60.7%	69%	49%	54%	67%	59%	66%
66.7%	64%	67%	71%	67%	67%	64%
76.8%	80%	61%	82%	75%	80%	83%
54.8%	39%	65%	69%	59%	32%	65%
55.2%	50%	53%	63%	59%	53%	53%