	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 74.8%	3rd 74.3%	4th 72.4%	1st 75.1%	6th 68.0%	5th 70.5%
58.5%	71%	48%	71%	58%	54%	49%
73.8%	78%	70%	66%	77%	73%	79%
87.3%	94%	91%	92%	93%	77%	77%
76.0%	90%	78%	72%	66%	70%	80%
73.5%	77%	41%	88%	81%	66%	88%
78.2%	89%	91%	93%	91%	61%	44%
71.7%	68%	65%	79%	69%	75%	74%
57.8%	65%	100%	56%	41%	41%	44%
63.3%	63%	81%	57%	61%	58%	60%
84.3%	92%	86%	65%	87%	87%	89%
72.2%	71%	80%	61%	72%	78%	71%
57.2%	53%	56%	53%	60%	60%	61%
61.2%	70%	84%	61%	70%	34%	48%
74.5%	77%	76%	79%	77%	68%	70%
81.2%	84%	81%	85%	85%	70%	82%
87.3%	87%	93%	91%	87%	83%	83%
71.5%	84%	73%	64%	78%	68%	62%
72.2%	77%	74%	68%	76%	67%	71%
80.0%	82%	83%	77%	83%	75%	80%
69.5%	71%	71%	70%	67%	64%	74%
74.0%	70%	66%	85%	87%	58%	78%
67.8%	71%	66%	64%	73%	65%	68%
57.8%	66%	72%	54%	53%	56%	46%
65.2%	69%	56%	70%	65%	66%	65%
64.3%	60%	68%	70%	68%	54%	66%
72.7%	73%	75%	86%	79%	49%	74%
83.0%	82%	92%	81%	82%	79%	82%
69.0%	77%	63%	65%	71%	71%	67%
81.5%	89%	81%	78%	79%	86%	76%
91.0%	91%	90%	94%	96%	92%	83%
51.3%	40%	74%	48%	56%	48%	42%
67.0%	66%	69%	69%	73%	59%	66%
79.0%	81%	80%	67%	83%	82%	81%
85.8%	85%	82%	84%	90%	82%	92%
57.5%	63%	63%	62%	66%	40%	51%
88.5%	84%	93%	93%	88%	90%	83%
83.7%	81%	82%	77%	87%	87%	88%
68.2%	69%	68%	71%	67%	64%	70%
59.7%	53%	45%	56%	70%	73%	61%
75.8%	78%	75%	78%	77%	74%	73%
65.7%	66%	69%	62%	71%	67%	59%
68.8%	69%	69%	59%	73%	73%	70%
73.2%	76%	68%	75%	75%	70%	75%
64.8%	69%	56%	75%	69%	63%	57%
87.5%	95%	94%	84%	81%	81%	90%
85.3%	87%	85%	82%	90%	92%	76%
64.3%	74%	65%	59%	65%	61%	62%
65.3%	73%	88%	50%	75%	44%	62%
78.7%	73%	73%	77%	78%	86%	85%
81.7%	72%	91%	84%	89%	61%	93%
75.3%	81%	74%	86%	82%	58%	71%
69.3%	65%	63%	75%	79%	72%	62%
76.0%	72%	90%	77%	65%	78%	74%
67.2%	77%	45%	66%	77%	63%	75%