	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 74.0%	3rd 72.5%	6th 69.6%	2nd 73.8%	5th 70.6%	4th 72.3%
31.5%	25%	59%	25%	23%	30%	27%
72.7%	74%	63%	75%	74%	74%	76%
81.0%	77%	81%	76%	84%	80%	88%
74.8%	73%	78%	70%	74%	72%	82%
85.7%	92%	86%	88%	90%	80%	78%
60.0%	62%	55%	78%	62%	57%	46%
67.7%	67%	62%	57%	80%	71%	69%
67.2%	76%	66%	60%	73%	63%	65%
83.3%	72%	91%	95%	72%	100%	70%
68.8%	74%	83%	65%	64%	64%	63%
71.8%	74%	76%	50%	76%	80%	75%
71.2%	81%	80%	73%	55%	69%	69%
68.5%	80%	76%	64%	70%	59%	62%
76.3%	79%	84%	75%	88%	60%	72%
32.2%	42%	37%	30%	16%	55%	13%
74.8%	80%	81%	58%	78%	74%	78%
83.0%	84%	73%	86%	78%	88%	89%
53.3%	69%	36%	55%	51%	59%	50%
73.3%	80%	54%	79%	81%	65%	81%
53.5%	70%	63%	45%	49%	49%	45%
75.5%	72%	77%	76%	75%	75%	78%
77.7%	80%	81%	63%	79%	84%	79%
80.7%	98%	84%	77%	77%	71%	77%
78.0%	79%	73%	72%	82%	86%	76%
45.3%	39%	45%	50%	35%	53%	50%
66.2%	67%	73%	56%	80%	52%	69%
76.5%	78%	75%	72%	71%	82%	81%
69.3%	78%	68%	63%	79%	60%	68%
75.5%	80%	83%	77%	70%	71%	72%
65.0%	86%	77%	35%	65%	71%	56%
79.5%	72%	84%	72%	84%	84%	81%
76.0%	81%	60%	79%	80%	78%	78%
66.8%	71%	67%	71%	69%	64%	59%
67.8%	60%	73%	72%	75%	55%	72%
77.7%	82%	71%	78%	80%	77%	78%
66.5%	68%	74%	57%	62%	70%	68%
67.0%	67%	52%	70%	71%	71%	71%
76.8%	77%	74%	77%	77%	77%	79%
81.3%	89%	89%	75%	85%	76%	74%
67.7%	73%	83%	52%	65%	71%	62%
58.3%	65%	56%	40%	58%	73%	58%
79.3%	83%	51%	86%	80%	86%	90%
71.0%	72%	76%	72%	79%	68%	59%
72.8%	80%	81%	60%	74%	66%	76%
74.5%	74%	76%	77%	80%	57%	83%
59.0%	58%	93%	33%	62%	49%	59%
83.8%	86%	78%	81%	86%	81%	91%
75.8%	68%	55%	78%	85%	91%	78%
63.5%	56%	62%	67%	69%	60%	67%
78.5%	78%	79%	79%	82%	75%	78%
77.2%	84%	69%	74%	81%	80%	75%
76.8%	82%	72%	84%	76%	68%	79%
77.3%	81%	81%	73%	77%	75%	77%
64.5%	64%	66%	61%	67%	66%	63%
73.2%	72%	71%	70%	72%	77%	77%
52.7%	54%	79%	30%	57%	30%	66%
77.0%	85%	80%	75%	81%	70%	71%
73.0%	72%	63%	77%	75%	75%	76%
69.2%	65%	76%	71%	75%	59%	69%
82.8%	92%	79%	61%	94%	79%	92%
63.8%	70%	75%	46%	57%	68%	67%
77.2%	78%	78%	79%	74%	79%	75%
66.8%	68%	51%	64%	70%	72%	76%
79.3%	79%	71%	76%	85%	82%	83%
77.5%	79%	75%	75%	81%	74%	81%
73.5%	83%	40%	80%	82%	78%	78%
68.7%	66%	74%	83%	63%	63%	63%
81.5%	81%	76%	80%	83%	84%	85%
86.2%	92%	88%	75%	94%	84%	84%
67.3%	0%	47%	93%	89%	87%	88%
83.2%	91%	80%	89%	89%	69%	81%
84.3%	89%	89%	87%	79%	83%	79%
47.8%	40%	55%	45%	48%	36%	63%
65.7%	70%	41%	63%	73%	73%	74%
84.2%	83%	84%	84%	88%	82%	84%
84.5%	81%	76%	78%	93%	91%	88%
94.0%	94%	94%	94%	94%	94%	94%
67.3%	57%	75%	68%	63%	68%	73%
80.5%	78%	70%	79%	88%	81%	87%
54.8%	61%	87%	41%	59%	44%	37%
62.7%	72%	100%	57%	59%	37%	51%
75.7%	81%	80%	79%	77%	72%	65%
84.5%	87%	86%	70%	89%	90%	85%
82.7%	80%	85%	92%	87%	65%	87%
85.5%	88%	78%	87%	77%	86%	97%
74.5%	77%	74%	73%	77%	73%	73%
68.3%	73%	75%	69%	62%	61%	70%
80.8%	89%	64%	79%	85%	85%	83%
83.2%	92%	75%	95%	87%	78%	72%
86.3%	87%	90%	89%	89%	84%	79%
64.5%	72%	70%	70%	67%	40%	68%