	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 67.2%	2nd 67.3%	5th 65.5%	4th 67.1%	6th 62.4%	1st 67.4%
74.3%	75%	77%	78%	79%	68%	69%
65.0%	59%	72%	59%	72%	64%	64%
70.7%	73%	91%	71%	71%	58%	60%
89.8%	88%	87%	83%	100%	83%	98%
70.8%	81%	65%	78%	74%	54%	73%
66.3%	58%	74%	62%	70%	67%	67%
79.2%	85%	91%	72%	75%	74%	78%
49.3%	48%	80%	23%	45%	66%	34%
68.7%	71%	71%	61%	72%	66%	71%
78.8%	73%	81%	78%	84%	82%	75%
65.0%	75%	85%	60%	62%	44%	64%
44.7%	38%	35%	60%	48%	35%	52%
86.2%	97%	79%	90%	81%	79%	91%
89.8%	88%	87%	83%	100%	83%	98%
66.2%	72%	65%	57%	65%	69%	69%
49.3%	56%	47%	39%	47%	46%	61%
72.2%	76%	69%	82%	71%	59%	76%
82.2%	80%	78%	81%	82%	85%	87%
66.3%	65%	68%	63%	64%	66%	72%
46.7%	51%	53%	50%	53%	33%	40%
69.0%	72%	78%	62%	70%	63%	69%
62.8%	72%	38%	61%	59%	59%	88%
96.5%	96%	94%	100%	92%	99%	98%
42.8%	46%	37%	39%	45%	43%	47%
86.2%	97%	79%	90%	81%	79%	91%
51.7%	50%	53%	60%	54%	39%	54%
35.8%	37%	23%	37%	39%	40%	39%
64.8%	56%	54%	77%	75%	56%	71%
89.0%	87%	94%	71%	85%	98%	99%
56.2%	53%	55%	57%	52%	60%	60%
66.8%	70%	69%	70%	62%	57%	73%
70.8%	70%	70%	75%	71%	71%	68%
74.0%	68%	72%	79%	77%	79%	69%
59.0%	59%	59%	60%	60%	59%	57%
48.0%	46%	49%	47%	47%	49%	50%
67.0%	57%	71%	73%	61%	71%	69%
52.3%	54%	51%	55%	54%	52%	48%
44.0%	41%	49%	48%	44%	38%	44%
48.2%	51%	51%	54%	58%	29%	46%
78.7%	74%	86%	74%	78%	76%	84%
61.3%	68%	69%	65%	62%	42%	62%
65.2%	66%	68%	62%	58%	71%	66%
78.3%	83%	85%	68%	83%	79%	72%
60.8%	59%	61%	65%	64%	55%	61%
63.2%	68%	58%	67%	72%	52%	62%
68.0%	81%	66%	66%	67%	73%	55%