	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	2nd 69.3%	5th 64.5%	6th 63.5%	1st 70.5%	4th 65.7%	3rd 67.7%
31.3%	25%	65%	22%	21%	33%	22%
56.2%	63%	70%	54%	50%	50%	50%
67.5%	69%	66%	61%	71%	66%	72%
64.0%	77%	73%	50%	73%	57%	54%
63.0%	58%	53%	57%	65%	75%	70%
46.7%	47%	51%	70%	56%	22%	34%
82.7%	83%	66%	75%	100%	80%	92%
62.2%	67%	72%	46%	73%	56%	59%
79.5%	67%	93%	86%	69%	93%	69%
71.3%	78%	100%	70%	62%	56%	62%
80.7%	83%	92%	87%	78%	70%	74%
75.5%	78%	59%	79%	83%	73%	81%
69.5%	71%	72%	65%	72%	65%	72%
70.3%	75%	75%	60%	70%	70%	72%
53.5%	63%	76%	57%	33%	59%	33%
86.7%	86%	93%	69%	100%	86%	86%
55.3%	63%	17%	63%	65%	61%	63%
74.8%	83%	62%	73%	83%	77%	71%
74.7%	71%	66%	83%	84%	70%	74%
53.3%	74%	54%	54%	42%	54%	42%
51.2%	56%	42%	51%	57%	57%	44%
60.8%	71%	55%	44%	75%	70%	50%
68.7%	57%	53%	74%	70%	80%	78%
61.3%	70%	25%	60%	74%	58%	81%
33.7%	22%	44%	38%	22%	38%	38%
70.5%	73%	70%	60%	72%	76%	72%
69.3%	72%	60%	63%	80%	67%	74%
61.8%	69%	72%	60%	63%	50%	57%
50.5%	54%	49%	58%	49%	44%	49%
69.3%	100%	100%	5%	60%	100%	51%
74.8%	69%	76%	71%	74%	74%	85%
63.7%	66%	54%	64%	65%	68%	65%
69.7%	65%	66%	65%	70%	78%	74%
78.2%	92%	77%	84%	75%	74%	67%
66.5%	73%	80%	63%	62%	59%	62%
63.2%	64%	64%	48%	65%	72%	66%
66.5%	67%	28%	75%	78%	74%	77%
72.2%	69%	47%	78%	87%	72%	80%
73.0%	74%	74%	66%	71%	72%	81%
51.0%	65%	78%	35%	42%	51%	35%
65.2%	74%	74%	45%	60%	78%	60%
76.8%	59%	55%	80%	86%	81%	100%
59.3%	51%	61%	75%	52%	42%	75%
70.2%	74%	74%	61%	74%	65%	73%
73.8%	79%	69%	70%	79%	74%	72%
53.0%	50%	81%	29%	76%	39%	43%
74.2%	77%	71%	68%	74%	76%	79%
66.3%	61%	43%	63%	79%	78%	74%
69.2%	73%	37%	80%	75%	70%	80%
70.7%	81%	58%	52%	74%	86%	73%
59.3%	67%	59%	50%	67%	58%	55%
55.3%	57%	45%	60%	62%	51%	57%
54.3%	60%	53%	46%	54%	59%	54%
77.5%	81%	73%	80%	81%	77%	73%
68.8%	71%	52%	62%	86%	65%	77%
53.7%	75%	73%	32%	65%	39%	38%
76.5%	88%	86%	70%	78%	71%	66%
61.3%	71%	56%	59%	66%	53%	63%
72.8%	70%	77%	66%	81%	65%	78%
87.3%	91%	83%	64%	93%	100%	93%
55.2%	69%	67%	43%	52%	56%	44%
56.7%	58%	64%	60%	57%	44%	57%
69.2%	76%	13%	87%	74%	78%	87%
65.3%	84%	53%	59%	61%	61%	74%
52.8%	56%	56%	55%	50%	50%	50%
54.3%	62%	14%	65%	65%	58%	62%
79.5%	80%	73%	73%	93%	78%	80%
65.0%	70%	62%	60%	68%	57%	73%
80.8%	81%	69%	85%	100%	78%	72%
59.2%	0%	44%	78%	90%	72%	71%
76.7%	79%	73%	91%	78%	60%	79%
70.2%	69%	72%	71%	69%	72%	68%
47.3%	39%	55%	38%	47%	27%	78%
51.3%	63%	15%	51%	62%	54%	63%
74.0%	74%	74%	74%	74%	74%	74%
72.0%	67%	64%	71%	75%	76%	79%
100.0%	100%	100%	100%	100%	100%	100%
53.0%	38%	64%	63%	43%	59%	51%
72.3%	85%	78%	56%	79%	77%	59%
50.3%	66%	60%	55%	60%	17%	44%
80.2%	76%	100%	66%	100%	39%	100%
89.0%	92%	92%	90%	92%	80%	88%
62.7%	76%	70%	45%	73%	63%	49%
74.0%	71%	79%	73%	71%	75%	75%
68.8%	68%	56%	65%	81%	71%	72%
61.3%	69%	60%	43%	64%	72%	60%
76.2%	80%	72%	78%	68%	73%	86%
72.0%	71%	41%	82%	80%	78%	80%
90.5%	91%	100%	87%	100%	79%	86%
94.0%	92%	93%	88%	100%	91%	100%
71.2%	65%	67%	72%	67%	78%	78%