	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 80.7%	1st 80.9%	6th 73.5%	3rd 78.4%	5th 74.4%	4th 75.8%
66.3%	78%	59%	74%	63%	64%	60%
89.5%	96%	85%	94%	91%	82%	89%
85.3%	91%	92%	89%	91%	75%	74%
74.2%	80%	83%	66%	71%	70%	75%
69.3%	78%	55%	64%	66%	77%	76%
74.2%	75%	79%	60%	80%	82%	69%
84.8%	90%	90%	64%	91%	90%	84%
61.3%	74%	100%	46%	44%	60%	44%
72.3%	68%	78%	68%	78%	70%	72%
79.7%	89%	87%	66%	84%	75%	77%
83.3%	75%	85%	85%	83%	86%	86%
78.5%	79%	66%	86%	84%	73%	83%
54.3%	63%	68%	55%	55%	43%	42%
86.5%	94%	90%	84%	88%	79%	84%
82.5%	89%	86%	74%	84%	74%	88%
89.2%	90%	94%	90%	89%	82%	90%
79.7%	84%	85%	72%	85%	78%	74%
84.2%	85%	90%	82%	85%	82%	81%
62.3%	72%	72%	63%	61%	50%	56%
80.7%	89%	92%	65%	80%	79%	79%
85.5%	92%	89%	76%	90%	75%	91%
83.2%	93%	91%	70%	86%	76%	83%
57.7%	57%	62%	62%	45%	71%	49%
82.0%	87%	75%	92%	76%	79%	83%
85.8%	90%	92%	84%	86%	71%	92%
84.3%	90%	95%	93%	88%	55%	85%
92.8%	88%	91%	96%	96%	94%	92%
79.0%	89%	90%	60%	82%	80%	73%
72.8%	81%	75%	61%	78%	75%	67%
70.2%	76%	73%	73%	73%	57%	69%
64.8%	69%	68%	57%	68%	67%	60%
74.0%	66%	72%	67%	72%	83%	84%
85.3%	81%	93%	66%	90%	90%	92%
84.2%	84%	88%	84%	85%	73%	91%
51.8%	54%	56%	54%	42%	58%	47%
88.5%	85%	91%	93%	88%	90%	84%
81.8%	87%	88%	69%	84%	84%	79%
61.3%	58%	64%	61%	62%	68%	55%
86.5%	84%	84%	87%	90%	88%	86%
83.7%	74%	91%	78%	89%	93%	77%
76.2%	74%	84%	69%	75%	81%	74%
73.0%	78%	77%	58%	77%	81%	67%
81.2%	86%	93%	78%	82%	73%	75%
76.0%	88%	70%	84%	76%	63%	75%
82.2%	84%	79%	76%	83%	85%	86%
71.8%	75%	79%	68%	75%	59%	75%
54.0%	63%	60%	53%	61%	37%	50%
67.5%	74%	71%	48%	74%	76%	62%
86.7%	88%	88%	87%	82%	94%	81%
77.2%	84%	85%	77%	79%	59%	79%
85.2%	94%	90%	93%	91%	58%	85%
87.0%	83%	85%	90%	90%	89%	85%
78.8%	74%	73%	73%	77%	88%	88%
82.2%	88%	68%	85%	88%	76%	88%