	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 72.7%	1st 73.8%	6th 65.1%	3rd 70.0%	5th 65.5%	4th 68.1%
73.5%	84%	75%	58%	73%	78%	73%
76.3%	81%	79%	74%	71%	77%	76%
83.7%	86%	92%	83%	83%	80%	78%
59.0%	61%	62%	52%	62%	44%	73%
85.5%	88%	81%	87%	86%	88%	83%
73.2%	84%	80%	54%	74%	80%	67%
70.0%	79%	79%	67%	64%	73%	58%
57.0%	70%	62%	37%	54%	65%	54%
82.3%	82%	92%	78%	81%	80%	81%
57.8%	65%	64%	53%	59%	42%	64%
71.5%	84%	58%	94%	81%	50%	62%
59.2%	78%	82%	40%	67%	30%	58%
71.2%	68%	81%	74%	74%	56%	74%
86.8%	88%	85%	91%	90%	83%	84%
66.0%	62%	70%	70%	67%	72%	55%
68.3%	77%	77%	52%	68%	70%	66%
61.8%	77%	71%	47%	59%	58%	59%
62.3%	76%	74%	43%	62%	64%	55%
63.5%	57%	55%	52%	77%	63%	77%
72.2%	63%	80%	70%	74%	85%	61%
66.0%	68%	71%	61%	63%	65%	68%
73.2%	76%	82%	58%	75%	77%	71%
49.5%	57%	58%	43%	55%	31%	53%
79.0%	77%	81%	91%	86%	59%	80%
82.5%	84%	81%	90%	82%	80%	78%
68.3%	70%	75%	60%	71%	69%	65%
51.8%	65%	71%	35%	43%	56%	41%
65.0%	71%	62%	56%	67%	67%	67%
57.5%	78%	80%	38%	61%	27%	61%
74.5%	81%	88%	67%	76%	61%	74%
73.2%	58%	75%	83%	63%	80%	80%
64.3%	62%	56%	65%	65%	68%	70%
74.2%	77%	83%	73%	73%	70%	69%
72.0%	52%	93%	74%	76%	71%	66%
48.3%	55%	60%	34%	48%	37%	56%
64.8%	68%	50%	77%	61%	64%	69%
65.5%	57%	54%	83%	64%	64%	71%
83.0%	89%	89%	92%	80%	76%	72%
67.8%	73%	71%	62%	69%	72%	60%
68.3%	66%	60%	69%	69%	72%	74%
68.3%	70%	69%	75%	70%	64%	62%
77.8%	85%	83%	57%	86%	73%	83%
80.0%	78%	81%	80%	82%	77%	82%