	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 65.7%	2nd 64.9%	5th 62.1%	3rd 64.7%	6th 60.1%	4th 63.7%
19.0%	20%	19%	18%	19%	21%	17%
66.5%	71%	55%	66%	63%	72%	72%
70.0%	69%	67%	71%	71%	71%	71%
64.2%	61%	63%	64%	64%	66%	67%
56.3%	56%	73%	71%	58%	29%	51%
72.7%	80%	61%	85%	80%	53%	77%
61.2%	59%	67%	50%	65%	63%	63%
73.8%	78%	89%	56%	73%	76%	71%
82.3%	64%	92%	93%	87%	84%	74%
66.7%	63%	76%	75%	57%	61%	68%
66.5%	65%	63%	77%	67%	62%	65%
76.2%	81%	75%	78%	74%	75%	74%
73.2%	75%	73%	76%	76%	63%	76%
67.7%	68%	74%	71%	61%	71%	61%
61.5%	71%	71%	63%	42%	73%	49%
91.0%	97%	99%	60%	100%	97%	93%
66.3%	65%	63%	73%	61%	68%	68%
57.8%	60%	62%	62%	61%	44%	58%
66.0%	64%	67%	66%	73%	63%	63%
37.3%	57%	34%	21%	51%	6%	55%
59.8%	57%	57%	67%	55%	63%	60%
80.3%	83%	89%	76%	78%	78%	78%
62.2%	68%	69%	61%	55%	53%	67%
42.5%	43%	41%	41%	47%	36%	47%
18.0%	14%	19%	22%	23%	17%	13%
56.2%	59%	43%	69%	43%	66%	57%
65.5%	69%	65%	67%	58%	60%	74%
75.5%	82%	58%	78%	77%	80%	78%
47.2%	48%	46%	33%	46%	58%	52%
68.5%	80%	64%	63%	76%	64%	64%
44.3%	43%	51%	51%	46%	18%	57%
69.5%	77%	55%	76%	71%	71%	67%
87.2%	85%	78%	87%	100%	84%	89%
56.0%	62%	55%	58%	51%	59%	51%
50.0%	50%	48%	49%	55%	41%	57%
52.0%	54%	58%	45%	52%	51%	52%
65.2%	63%	61%	65%	68%	67%	67%
64.3%	56%	68%	61%	65%	59%	77%
73.7%	76%	71%	79%	69%	77%	70%
46.7%	49%	58%	33%	51%	47%	42%
67.2%	70%	65%	56%	73%	71%	68%
65.8%	74%	52%	67%	72%	58%	72%
69.5%	71%	71%	67%	69%	67%	72%
59.8%	64%	49%	59%	64%	62%	61%
68.3%	62%	61%	74%	74%	54%	85%
65.5%	71%	81%	59%	68%	57%	57%
60.7%	62%	63%	56%	67%	55%	61%
63.3%	54%	62%	69%	69%	54%	72%
78.0%	80%	75%	75%	83%	82%	73%
69.8%	72%	73%	63%	76%	67%	68%
60.8%	67%	74%	48%	59%	62%	55%
69.5%	76%	74%	66%	67%	73%	61%
57.8%	49%	46%	64%	61%	56%	71%
73.3%	81%	77%	72%	72%	65%	73%
66.0%	64%	64%	72%	66%	60%	70%
71.3%	81%	65%	63%	89%	59%	71%
63.3%	72%	61%	60%	70%	51%	66%
56.5%	64%	77%	42%	57%	54%	45%
71.3%	70%	60%	73%	73%	73%	79%
91.2%	97%	92%	74%	93%	97%	94%
56.8%	56%	56%	51%	60%	55%	63%
71.3%	67%	62%	84%	66%	71%	78%
69.0%	64%	64%	69%	75%	74%	68%
47.8%	46%	51%	45%	49%	47%	49%
72.7%	71%	52%	78%	78%	78%	79%
59.5%	56%	57%	62%	58%	62%	62%
76.0%	75%	79%	77%	77%	71%	77%
63.2%	66%	68%	65%	69%	47%	64%
51.0%	51%	58%	51%	58%	37%	51%
75.2%	83%	50%	84%	79%	84%	71%
54.0%	55%	55%	57%	50%	57%	50%
58.3%	73%	68%	55%	68%	18%	68%
53.5%	53%	64%	44%	56%	64%	40%
57.3%	54%	63%	66%	49%	54%	58%
41.8%	43%	51%	51%	51%	0%	55%
68.2%	74%	70%	64%	66%	69%	66%
74.7%	77%	73%	71%	73%	77%	77%
40.5%	37%	40%	54%	39%	36%	37%
75.3%	80%	76%	71%	78%	74%	73%
55.7%	75%	90%	10%	77%	28%	54%
61.0%	74%	100%	47%	51%	58%	36%
77.2%	86%	83%	62%	81%	83%	68%
63.3%	68%	71%	58%	61%	61%	61%
50.0%	58%	51%	45%	54%	50%	42%
72.8%	78%	77%	64%	80%	69%	69%
67.3%	71%	74%	59%	69%	68%	63%
66.3%	70%	74%	68%	55%	63%	68%
57.5%	49%	63%	61%	46%	72%	54%
67.5%	72%	71%	79%	65%	61%	57%
84.5%	87%	84%	83%	86%	81%	86%
62.7%	63%	70%	64%	57%	58%	64%