	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 81.2%	1st 81.2%	6th 71.9%	3rd 77.7%	5th 73.5%	4th 75.0%
56.7%	60%	48%	62%	60%	60%	50%
76.7%	85%	63%	74%	73%	71%	94%
73.8%	86%	82%	67%	72%	69%	67%
74.7%	76%	77%	77%	81%	68%	69%
83.0%	84%	86%	82%	69%	83%	94%
80.8%	79%	86%	78%	76%	82%	84%
90.2%	95%	92%	80%	90%	95%	89%
56.5%	67%	92%	47%	38%	57%	38%
63.3%	61%	72%	56%	73%	65%	53%
77.7%	82%	82%	68%	76%	75%	83%
93.3%	88%	98%	91%	92%	94%	97%
90.2%	91%	92%	89%	90%	89%	90%
43.0%	65%	59%	10%	51%	44%	29%
85.3%	87%	89%	75%	90%	81%	90%
83.8%	94%	84%	77%	83%	82%	83%
84.3%	90%	89%	73%	87%	75%	92%
78.2%	80%	87%	67%	89%	75%	71%
74.8%	77%	84%	66%	77%	80%	65%
69.5%	82%	79%	68%	72%	50%	66%
67.2%	69%	73%	51%	73%	75%	62%
82.8%	83%	90%	72%	88%	76%	88%
85.3%	96%	93%	69%	93%	81%	80%
52.2%	51%	58%	53%	45%	59%	47%
79.8%	87%	84%	75%	79%	75%	79%
81.2%	83%	87%	78%	84%	71%	84%
84.2%	94%	93%	83%	85%	66%	84%
92.5%	95%	91%	90%	95%	93%	91%
71.2%	81%	84%	60%	65%	77%	60%
80.5%	87%	83%	74%	85%	81%	73%
65.8%	65%	79%	69%	68%	51%	63%
63.5%	64%	69%	45%	77%	69%	57%
85.7%	82%	90%	86%	86%	79%	91%
79.2%	82%	85%	72%	79%	81%	76%
82.8%	83%	86%	82%	83%	78%	85%
58.8%	64%	71%	56%	57%	53%	52%
83.5%	88%	87%	82%	75%	81%	88%
81.8%	85%	88%	75%	81%	84%	78%
64.5%	72%	72%	68%	69%	53%	53%
86.8%	88%	82%	91%	87%	88%	85%
89.8%	91%	93%	91%	92%	94%	78%
88.8%	91%	80%	90%	93%	93%	86%
72.8%	83%	79%	59%	71%	78%	67%
76.8%	79%	85%	66%	80%	72%	79%
84.0%	95%	81%	92%	94%	62%	80%
82.2%	85%	80%	83%	77%	84%	84%
71.3%	69%	68%	75%	78%	61%	77%
63.3%	76%	80%	60%	62%	44%	58%
67.7%	74%	72%	55%	72%	70%	63%
73.3%	82%	76%	61%	69%	76%	76%
79.8%	84%	83%	82%	80%	71%	79%
82.7%	90%	89%	88%	82%	63%	84%
87.0%	84%	81%	91%	89%	86%	91%
86.5%	88%	88%	82%	84%	86%	91%
73.3%	87%	66%	68%	80%	61%	78%