	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 81.7%	1st 81.8%	5th 76.1%	3rd 80.7%	6th 75.9%	4th 78.5%
79.0%	87%	81%	62%	83%	86%	75%
89.0%	92%	89%	91%	89%	80%	93%
69.8%	67%	64%	75%	75%	68%	70%
70.3%	74%	74%	72%	67%	60%	75%
92.8%	89%	89%	96%	96%	94%	93%
81.5%	89%	83%	74%	76%	91%	76%
81.2%	73%	88%	80%	82%	90%	74%
76.3%	67%	84%	67%	81%	78%	81%
88.7%	88%	87%	87%	88%	91%	91%
66.3%	67%	76%	68%	65%	51%	71%
83.3%	92%	80%	92%	84%	75%	77%
65.3%	70%	77%	69%	66%	52%	58%
86.5%	95%	91%	87%	85%	68%	93%
88.3%	87%	92%	87%	92%	86%	86%
84.2%	89%	86%	81%	87%	76%	86%
78.7%	82%	80%	67%	89%	80%	74%
69.3%	73%	76%	79%	62%	70%	56%
63.0%	67%	64%	49%	71%	69%	58%
66.0%	64%	66%	58%	70%	64%	74%
86.0%	78%	85%	91%	87%	93%	82%
83.7%	87%	86%	74%	88%	87%	80%
84.7%	87%	88%	72%	88%	81%	92%
78.7%	85%	86%	74%	87%	61%	79%
83.5%	80%	89%	83%	88%	73%	88%
89.3%	89%	95%	86%	93%	84%	89%
79.7%	80%	82%	73%	83%	78%	82%
64.8%	69%	69%	53%	67%	74%	57%
78.5%	90%	88%	66%	78%	85%	64%
66.5%	88%	75%	66%	70%	38%	62%
71.3%	75%	84%	67%	73%	66%	63%
82.0%	86%	83%	81%	83%	69%	90%
80.5%	84%	84%	75%	80%	80%	80%
67.7%	64%	62%	72%	72%	69%	67%
79.8%	78%	89%	77%	79%	83%	73%
70.8%	80%	61%	65%	64%	63%	92%
82.3%	87%	71%	88%	82%	83%	83%
86.2%	87%	92%	89%	88%	71%	90%
82.3%	94%	82%	81%	82%	78%	77%
77.3%	79%	84%	64%	79%	82%	76%
96.2%	96%	94%	95%	95%	97%	100%
83.2%	86%	95%	73%	84%	78%	83%
79.2%	81%	76%	74%	79%	82%	83%
88.3%	92%	92%	93%	91%	80%	82%