	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 78.7%	3rd 77.7%	5th 71.3%	1st 78.8%	6th 70.1%	4th 75.8%
93.3%	94%	93%	95%	92%	96%	90%
61.5%	76%	73%	48%	52%	62%	58%
61.2%	81%	75%	49%	64%	49%	49%
98.0%	98%	98%	98%	98%	98%	98%
84.8%	81%	85%	95%	88%	83%	77%
61.3%	39%	66%	66%	61%	62%	74%
85.8%	89%	92%	89%	89%	72%	84%
59.5%	56%	71%	40%	95%	44%	51%
59.3%	51%	83%	59%	70%	43%	50%
72.7%	75%	79%	61%	87%	63%	71%
77.0%	88%	92%	75%	78%	59%	70%
68.5%	78%	67%	73%	80%	51%	62%
84.0%	94%	89%	90%	90%	60%	81%
98.0%	98%	98%	98%	98%	98%	98%
70.2%	79%	65%	52%	75%	79%	71%
87.2%	89%	94%	90%	70%	92%	88%
81.7%	82%	83%	80%	84%	75%	86%
76.3%	86%	77%	73%	74%	64%	84%
68.5%	83%	72%	59%	72%	54%	71%
65.8%	71%	80%	66%	70%	54%	54%
64.3%	67%	61%	59%	71%	63%	65%
69.3%	84%	43%	83%	67%	53%	86%
93.0%	99%	95%	85%	86%	94%	99%
80.3%	88%	67%	74%	80%	86%	87%
83.0%	97%	95%	96%	83%	53%	74%
61.3%	59%	71%	69%	72%	41%	56%
75.0%	74%	45%	66%	82%	91%	92%
60.5%	0%	69%	71%	87%	62%	74%
77.3%	86%	96%	10%	86%	93%	93%
63.0%	67%	67%	50%	73%	55%	66%
93.2%	92%	96%	95%	92%	96%	88%
71.5%	74%	76%	63%	77%	66%	73%
72.3%	86%	78%	59%	82%	61%	68%
65.3%	74%	63%	72%	60%	60%	63%
84.3%	85%	83%	92%	77%	87%	82%
84.8%	83%	85%	83%	87%	85%	86%
85.0%	88%	91%	79%	82%	90%	80%
66.0%	79%	33%	71%	69%	75%	69%
68.5%	78%	72%	54%	79%	64%	64%
68.3%	86%	58%	59%	75%	66%	66%
85.3%	90%	90%	84%	87%	76%	85%
75.8%	73%	81%	76%	83%	52%	90%
59.2%	70%	76%	40%	53%	64%	52%
74.8%	71%	76%	55%	86%	79%	82%
88.3%	88%	89%	93%	81%	81%	98%
83.8%	93%	86%	84%	83%	75%	82%