	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 75.4%	1st 77.7%	6th 64.8%	3rd 73.7%	5th 66.1%	4th 73.1%
53.2%	46%	63%	48%	52%	46%	64%
58.7%	69%	69%	41%	52%	64%	57%
54.0%	63%	61%	48%	53%	47%	52%
69.7%	75%	67%	59%	70%	73%	74%
75.3%	81%	85%	64%	68%	76%	78%
73.3%	66%	87%	71%	72%	80%	64%
86.0%	81%	90%	87%	86%	86%	86%
73.7%	75%	73%	68%	77%	82%	67%
65.5%	67%	81%	57%	60%	62%	66%
80.3%	84%	89%	82%	79%	72%	76%
74.0%	79%	94%	74%	72%	53%	72%
72.2%	70%	81%	89%	67%	51%	75%
77.0%	92%	99%	53%	88%	49%	81%
68.7%	73%	67%	57%	70%	72%	73%
66.7%	68%	63%	57%	70%	71%	71%
58.7%	66%	70%	46%	61%	51%	58%
69.3%	84%	73%	52%	72%	67%	68%
76.5%	84%	81%	57%	80%	79%	78%
73.0%	79%	82%	59%	75%	73%	70%
64.7%	67%	75%	70%	72%	37%	67%
69.7%	68%	72%	64%	71%	71%	72%
65.8%	75%	56%	53%	70%	58%	83%
94.7%	99%	99%	86%	86%	99%	99%
84.5%	85%	93%	81%	81%	77%	90%
70.3%	86%	92%	47%	81%	42%	74%
65.5%	57%	70%	88%	60%	48%	70%
78.7%	74%	72%	75%	84%	83%	84%
77.8%	81%	72%	87%	84%	61%	82%
77.0%	86%	88%	10%	90%	93%	95%
61.0%	70%	78%	35%	60%	68%	55%
52.8%	46%	56%	52%	57%	48%	58%
69.0%	69%	71%	71%	73%	63%	67%
74.2%	82%	75%	72%	75%	68%	73%
67.2%	67%	92%	68%	58%	57%	61%
81.0%	89%	77%	86%	88%	65%	81%
80.8%	82%	85%	59%	90%	82%	87%
75.5%	80%	81%	74%	70%	68%	80%
75.2%	82%	78%	69%	80%	67%	75%
67.5%	66%	75%	74%	81%	46%	63%
70.5%	79%	70%	64%	79%	65%	66%
74.5%	85%	79%	58%	75%	76%	74%
76.8%	75%	77%	81%	84%	63%	81%
57.3%	70%	65%	36%	62%	62%	49%
75.5%	69%	77%	83%	80%	64%	80%
88.2%	90%	94%	85%	93%	76%	91%
81.5%	88%	80%	82%	83%	81%	75%