	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 78.1%	1st 80.0%	6th 70.3%	3rd 75.4%	5th 71.4%	4th 74.8%
78.0%	81%	88%	60%	77%	84%	78%
84.3%	77%	68%	92%	83%	93%	93%
79.3%	74%	80%	88%	80%	72%	82%
58.3%	66%	68%	58%	58%	34%	66%
91.3%	90%	91%	85%	96%	93%	93%
74.3%	84%	85%	67%	70%	66%	74%
83.2%	82%	93%	83%	78%	93%	70%
64.2%	63%	74%	48%	60%	74%	66%
81.0%	79%	86%	72%	79%	87%	83%
50.2%	56%	55%	51%	48%	36%	55%
81.5%	84%	83%	83%	91%	76%	72%
49.7%	63%	56%	41%	48%	36%	54%
86.5%	94%	90%	81%	85%	84%	85%
87.5%	92%	89%	88%	89%	76%	91%
86.5%	95%	87%	86%	87%	77%	87%
69.7%	73%	76%	52%	74%	76%	67%
65.2%	68%	86%	63%	66%	51%	57%
59.7%	64%	72%	41%	62%	63%	56%
67.0%	71%	72%	52%	73%	68%	66%
79.3%	74%	87%	81%	77%	82%	75%
78.5%	91%	75%	67%	83%	78%	77%
78.2%	81%	86%	65%	82%	84%	71%
72.8%	79%	80%	72%	82%	45%	79%
82.5%	92%	89%	74%	80%	71%	89%
86.8%	89%	89%	90%	88%	78%	87%
76.8%	75%	81%	71%	79%	75%	80%
68.5%	76%	75%	58%	64%	76%	62%
68.7%	77%	86%	53%	55%	76%	65%
52.5%	68%	65%	39%	66%	24%	53%
68.7%	58%	92%	59%	72%	67%	64%
85.5%	88%	87%	87%	87%	80%	84%
70.0%	75%	69%	60%	69%	72%	75%
71.7%	67%	75%	78%	72%	69%	69%
79.3%	74%	86%	78%	81%	86%	71%
60.7%	71%	57%	54%	53%	54%	75%
72.5%	79%	61%	79%	73%	73%	70%
89.8%	97%	85%	94%	89%	86%	88%
88.5%	92%	95%	94%	81%	77%	92%
68.3%	73%	76%	60%	66%	74%	61%
94.7%	91%	94%	97%	96%	94%	96%
79.0%	79%	90%	75%	76%	74%	80%
70.5%	70%	71%	60%	77%	64%	81%
84.0%	88%	88%	89%	89%	74%	76%