	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 67.8%	6th 62.9%	4th 64.3%	2nd 66.7%	5th 63.8%	3rd 65.1%
23.0%	8%	90%	8%	8%	16%	8%
75.7%	84%	41%	80%	83%	83%	83%
67.0%	64%	77%	62%	66%	70%	63%
66.7%	65%	60%	71%	69%	66%	69%
66.5%	73%	78%	71%	65%	58%	54%
69.0%	78%	48%	80%	77%	53%	78%
54.3%	64%	35%	52%	62%	60%	53%
69.8%	76%	69%	61%	78%	69%	66%
84.5%	73%	93%	93%	74%	100%	74%
64.5%	59%	80%	64%	61%	63%	60%
67.7%	64%	72%	72%	68%	65%	65%
71.7%	78%	62%	76%	74%	78%	62%
77.2%	73%	85%	76%	77%	63%	89%
60.8%	58%	63%	62%	58%	61%	63%
63.3%	71%	93%	63%	45%	63%	45%
94.5%	97%	100%	80%	100%	97%	93%
61.2%	68%	22%	73%	71%	65%	68%
61.3%	71%	58%	62%	61%	58%	58%
60.3%	63%	58%	65%	74%	50%	52%
51.5%	62%	55%	46%	51%	51%	44%
63.2%	61%	60%	67%	60%	60%	71%
69.5%	78%	77%	55%	76%	78%	53%
61.3%	70%	70%	58%	55%	48%	67%
41.3%	46%	17%	42%	46%	40%	57%
26.2%	12%	77%	18%	12%	25%	13%
60.0%	67%	43%	75%	48%	67%	60%
70.0%	68%	60%	78%	62%	73%	79%
70.8%	76%	72%	77%	71%	52%	77%
52.8%	49%	54%	64%	46%	52%	52%
60.8%	58%	58%	42%	63%	64%	80%
84.3%	74%	68%	93%	78%	100%	93%
66.5%	79%	36%	68%	76%	73%	67%
85.5%	92%	78%	89%	92%	85%	77%
59.2%	64%	71%	58%	54%	54%	54%
53.2%	55%	48%	49%	55%	55%	57%
55.8%	62%	48%	52%	58%	57%	58%
64.3%	67%	48%	73%	74%	62%	62%
65.0%	59%	64%	61%	65%	68%	73%
73.7%	74%	74%	70%	69%	77%	78%
44.5%	58%	54%	33%	40%	40%	42%
70.3%	73%	71%	59%	73%	69%	77%
66.7%	72%	52%	62%	72%	71%	71%
76.0%	68%	77%	91%	73%	68%	79%
64.7%	70%	68%	65%	71%	51%	63%
76.2%	76%	72%	79%	77%	80%	73%
63.7%	71%	78%	44%	93%	41%	55%
64.7%	64%	55%	57%	72%	68%	72%
61.2%	61%	27%	71%	68%	70%	70%
62.7%	83%	52%	49%	61%	74%	57%
62.0%	76%	59%	50%	68%	59%	60%
63.2%	71%	72%	53%	65%	59%	59%
63.2%	78%	60%	60%	67%	67%	47%
67.7%	71%	53%	66%	68%	69%	79%
74.7%	81%	75%	73%	73%	73%	73%
71.8%	73%	65%	69%	73%	77%	74%
69.8%	86%	47%	56%	89%	70%	71%
70.5%	80%	72%	69%	70%	66%	66%
56.5%	61%	88%	45%	57%	49%	39%
85.5%	90%	77%	90%	90%	77%	89%
86.0%	88%	100%	66%	85%	86%	91%
56.8%	61%	53%	53%	60%	54%	60%
73.2%	76%	58%	77%	64%	78%	86%
57.2%	56%	27%	68%	57%	69%	66%
48.5%	47%	41%	45%	51%	51%	56%
83.3%	90%	78%	83%	83%	83%	83%
54.8%	62%	15%	69%	59%	62%	62%
72.5%	73%	57%	77%	73%	76%	79%
65.0%	71%	37%	65%	69%	71%	77%
54.3%	64%	58%	51%	51%	51%	51%
74.0%	67%	47%	83%	88%	70%	89%
57.3%	57%	59%	50%	61%	53%	64%
68.2%	63%	67%	62%	73%	62%	82%
35.5%	33%	64%	31%	32%	20%	33%
54.2%	63%	17%	69%	54%	63%	59%
100.0%	100%	100%	100%	100%	100%	100%
70.0%	70%	69%	77%	72%	66%	66%
80.0%	80%	80%	80%	80%	80%	80%
38.8%	32%	18%	61%	32%	49%	41%
73.8%	73%	71%	71%	73%	77%	78%
62.2%	75%	90%	54%	72%	34%	48%
75.3%	71%	100%	64%	100%	58%	59%
85.7%	85%	92%	90%	88%	78%	81%
57.3%	61%	71%	45%	58%	61%	48%
48.0%	54%	60%	46%	44%	44%	40%
66.8%	68%	50%	69%	80%	69%	65%
61.0%	69%	68%	46%	71%	58%	54%
62.7%	69%	64%	61%	57%	57%	68%
53.2%	46%	48%	66%	53%	60%	46%
66.5%	68%	71%	79%	66%	57%	58%
87.0%	84%	92%	78%	92%	84%	92%
63.8%	68%	63%	68%	68%	46%	70%