	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 81.4%	3rd 80.7%	6th 75.1%	1st 83.5%	5th 75.4%	4th 79.0%
92.7%	89%	94%	95%	93%	94%	91%
67.2%	74%	75%	54%	60%	72%	68%
59.8%	72%	50%	57%	70%	54%	56%
99.0%	99%	99%	99%	99%	99%	99%
87.0%	77%	93%	96%	88%	84%	84%
72.0%	52%	75%	74%	65%	83%	83%
89.7%	87%	88%	93%	91%	89%	90%
60.2%	60%	66%	48%	75%	54%	58%
73.7%	77%	86%	66%	98%	50%	65%
76.7%	76%	81%	66%	83%	77%	77%
77.2%	83%	88%	81%	77%	63%	71%
71.3%	76%	62%	80%	79%	54%	77%
79.5%	89%	90%	66%	95%	66%	71%
99.0%	99%	99%	99%	99%	99%	99%
71.8%	80%	75%	51%	79%	74%	72%
85.5%	89%	83%	94%	71%	92%	84%
92.7%	94%	94%	93%	91%	91%	93%
82.5%	90%	87%	75%	86%	74%	83%
76.8%	80%	85%	69%	83%	62%	82%
69.7%	80%	75%	68%	74%	55%	66%
74.8%	76%	74%	76%	78%	71%	74%
73.3%	86%	43%	72%	70%	82%	87%
92.3%	96%	89%	92%	87%	94%	96%
74.3%	72%	86%	63%	77%	70%	78%
78.0%	86%	93%	62%	95%	64%	68%
72.7%	69%	72%	80%	84%	53%	78%
82.5%	91%	68%	70%	95%	88%	83%
83.7%	83%	69%	90%	93%	82%	85%
81.2%	90%	99%	10%	93%	96%	99%
69.5%	63%	72%	64%	77%	68%	73%
89.3%	91%	87%	93%	90%	82%	93%
77.2%	78%	79%	77%	79%	74%	76%
76.3%	73%	83%	63%	85%	81%	73%
75.8%	80%	93%	76%	74%	57%	75%
89.8%	89%	93%	93%	87%	86%	91%
82.7%	78%	84%	89%	81%	83%	81%
87.5%	88%	90%	86%	90%	90%	81%
67.7%	74%	70%	64%	69%	65%	64%
60.3%	64%	57%	59%	78%	44%	60%
81.3%	90%	62%	79%	92%	83%	82%
94.8%	95%	96%	95%	96%	92%	95%
81.0%	76%	90%	82%	88%	84%	66%
65.5%	71%	79%	53%	65%	63%	62%
74.8%	74%	75%	67%	85%	70%	78%
88.8%	91%	84%	92%	92%	86%	88%
83.3%	97%	81%	82%	85%	74%	81%