	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%	1st 76.0%	5th 68.4%	3rd 73.1%	4th 68.6%	6th 67.1%
57.3%	68%	50%	57%	63%	59%	47%
68.0%	80%	82%	69%	77%	44%	56%
85.2%	88%	96%	91%	86%	74%	76%
59.3%	60%	69%	57%	56%	54%	60%
64.7%	72%	45%	78%	63%	65%	65%
68.8%	75%	78%	81%	74%	69%	36%
67.2%	72%	77%	55%	67%	64%	68%
62.3%	77%	100%	53%	22%	70%	52%
62.3%	61%	57%	57%	63%	62%	74%
70.8%	74%	75%	55%	76%	76%	69%
76.2%	77%	80%	72%	77%	74%	77%
87.5%	90%	91%	93%	83%	85%	83%
52.3%	61%	87%	41%	70%	22%	33%
74.2%	77%	86%	75%	81%	51%	75%
75.3%	78%	76%	79%	75%	61%	83%
69.8%	81%	72%	72%	80%	52%	62%
57.8%	56%	68%	53%	58%	66%	46%
76.0%	81%	73%	76%	83%	61%	82%
82.5%	93%	87%	89%	82%	85%	59%
84.5%	89%	89%	79%	85%	90%	75%
80.0%	75%	77%	84%	83%	79%	82%
82.3%	86%	94%	62%	85%	89%	78%
51.5%	63%	57%	53%	33%	60%	43%
76.3%	83%	55%	83%	79%	80%	78%
68.8%	62%	64%	86%	75%	52%	74%
82.0%	83%	82%	79%	86%	77%	85%
91.3%	95%	97%	79%	93%	90%	94%
82.0%	90%	87%	73%	84%	84%	74%
66.3%	75%	72%	50%	77%	68%	56%
78.0%	78%	78%	78%	78%	78%	78%
40.0%	34%	75%	27%	34%	23%	47%
72.5%	80%	68%	65%	81%	77%	64%
67.8%	71%	74%	52%	74%	71%	65%
67.2%	71%	67%	62%	71%	68%	64%
57.2%	59%	72%	60%	58%	63%	31%
71.5%	81%	82%	66%	69%	64%	67%
83.2%	90%	87%	68%	88%	87%	79%
65.8%	59%	75%	65%	73%	71%	52%
73.0%	75%	61%	81%	74%	71%	76%
81.8%	85%	72%	81%	84%	84%	85%
68.3%	70%	79%	64%	70%	64%	63%
59.8%	68%	69%	48%	56%	60%	58%
71.0%	72%	95%	62%	75%	53%	69%
67.3%	67%	65%	79%	69%	64%	60%
87.2%	92%	91%	67%	92%	88%	93%
71.8%	61%	76%	64%	82%	78%	70%
52.0%	67%	60%	43%	45%	55%	42%
63.2%	67%	77%	47%	65%	69%	54%
86.2%	93%	95%	87%	84%	75%	83%
77.5%	68%	82%	87%	87%	80%	61%
83.2%	83%	85%	82%	85%	82%	82%
75.7%	71%	77%	79%	75%	76%	76%
87.0%	89%	77%	92%	87%	84%	93%
61.3%	68%	42%	55%	76%	57%	70%