	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 81.6%	3rd 80.4%	6th 75.8%	1st 82.0%	5th 77.6%	4th 78.5%
88.0%	89%	88%	84%	93%	91%	83%
67.5%	76%	72%	54%	59%	79%	65%
60.8%	82%	60%	54%	68%	50%	51%
99.0%	99%	99%	99%	99%	99%	99%
83.0%	83%	88%	91%	85%	77%	74%
74.7%	54%	71%	80%	71%	86%	86%
88.8%	80%	90%	94%	91%	91%	87%
58.5%	56%	79%	45%	70%	51%	50%
75.5%	74%	92%	70%	87%	65%	65%
76.0%	74%	82%	66%	81%	78%	75%
71.7%	80%	72%	76%	73%	73%	56%
76.5%	80%	61%	87%	87%	60%	84%
84.3%	94%	94%	91%	91%	53%	83%
99.0%	99%	99%	99%	99%	99%	99%
76.7%	78%	77%	63%	81%	85%	76%
84.2%	77%	88%	92%	72%	90%	86%
92.8%	94%	91%	93%	96%	91%	92%
83.2%	88%	85%	71%	85%	85%	85%
78.8%	85%	87%	64%	80%	78%	79%
68.7%	84%	69%	73%	74%	55%	57%
80.5%	84%	85%	78%	83%	72%	81%
75.3%	88%	50%	70%	67%	89%	88%
94.0%	97%	97%	88%	88%	97%	97%
72.5%	78%	57%	66%	81%	78%	75%
86.2%	97%	97%	95%	95%	51%	82%
71.5%	73%	69%	81%	86%	52%	68%
77.7%	75%	69%	64%	84%	87%	87%
86.2%	91%	73%	90%	92%	83%	88%
81.5%	94%	95%	10%	94%	99%	97%
66.2%	64%	69%	60%	74%	62%	68%
90.7%	91%	87%	90%	93%	91%	92%
77.2%	81%	84%	71%	81%	73%	73%
69.2%	69%	75%	59%	72%	72%	68%
83.3%	92%	83%	87%	83%	71%	84%
85.7%	78%	94%	91%	77%	90%	84%
84.5%	77%	88%	87%	78%	87%	90%
77.7%	79%	83%	76%	81%	86%	61%
68.3%	71%	63%	67%	68%	72%	69%
66.3%	68%	58%	65%	80%	63%	64%
87.2%	91%	72%	85%	97%	89%	89%
91.5%	94%	92%	96%	91%	88%	88%
77.7%	71%	88%	78%	77%	77%	75%
62.8%	66%	79%	46%	59%	67%	60%
74.5%	73%	71%	66%	82%	76%	79%
91.8%	94%	87%	93%	84%	96%	97%
81.2%	92%	90%	80%	82%	66%	77%