	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 78.6%	3rd 77.8%	6th 72.5%	1st 80.0%	5th 73.2%	4th 76.7%
60.2%	68%	53%	56%	67%	53%	64%
68.0%	70%	81%	52%	62%	74%	69%
64.8%	90%	71%	46%	74%	51%	57%
99.0%	99%	99%	99%	99%	99%	99%
80.3%	64%	87%	77%	79%	85%	90%
79.3%	71%	78%	80%	75%	89%	83%
86.5%	78%	81%	90%	92%	88%	90%
60.3%	61%	68%	51%	57%	63%	62%
70.0%	74%	85%	59%	89%	49%	64%
82.5%	88%	87%	66%	89%	87%	78%
77.2%	91%	92%	76%	73%	72%	59%
68.7%	68%	55%	81%	83%	57%	68%
83.3%	83%	92%	90%	94%	57%	84%
99.0%	99%	99%	99%	99%	99%	99%
73.5%	78%	81%	63%	70%	79%	70%
55.2%	67%	46%	54%	61%	45%	58%
88.3%	89%	94%	88%	89%	85%	85%
78.8%	83%	79%	70%	84%	77%	80%
72.0%	75%	85%	61%	70%	72%	69%
66.3%	77%	64%	70%	77%	53%	57%
75.8%	78%	78%	72%	75%	73%	79%
64.3%	74%	45%	58%	65%	73%	71%
90.3%	85%	96%	94%	85%	91%	91%
75.7%	76%	79%	70%	73%	75%	81%
82.8%	80%	95%	95%	91%	54%	82%
76.2%	72%	80%	86%	84%	67%	68%
79.7%	81%	65%	76%	95%	76%	85%
84.3%	93%	72%	87%	92%	75%	87%
81.8%	93%	96%	10%	98%	96%	98%
65.7%	67%	70%	61%	61%	69%	66%
60.8%	64%	52%	57%	72%	58%	62%
74.3%	78%	75%	75%	80%	66%	72%
74.0%	81%	79%	59%	76%	79%	70%
78.8%	90%	81%	81%	84%	59%	78%
88.5%	89%	93%	94%	88%	81%	86%
86.7%	78%	94%	87%	82%	88%	91%
74.7%	79%	62%	79%	78%	84%	66%
68.7%	74%	69%	64%	69%	70%	66%
64.8%	67%	61%	60%	75%	63%	63%
82.8%	80%	76%	83%	95%	79%	84%
82.3%	85%	85%	87%	82%	60%	95%
85.3%	80%	90%	86%	85%	86%	85%
63.3%	60%	74%	49%	61%	72%	64%
72.0%	67%	71%	63%	77%	77%	77%
87.7%	92%	80%	93%	88%	80%	93%
82.8%	79%	85%	79%	88%	81%	85%