	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	3rd 67.9%	1st 68.2%	5th 63.2%	4th 67.5%	6th 61.9%	2nd 68.0%
47.3%	43%	53%	53%	37%	37%	61%
55.8%	65%	62%	47%	44%	61%	56%
79.5%	87%	84%	80%	77%	71%	78%
82.2%	79%	82%	69%	86%	86%	91%
64.3%	66%	68%	73%	71%	51%	57%
51.3%	44%	73%	45%	58%	44%	44%
67.7%	68%	69%	64%	70%	64%	71%
74.5%	90%	49%	74%	91%	73%	70%
63.8%	77%	65%	68%	61%	56%	56%
85.3%	91%	94%	82%	83%	78%	84%
55.3%	63%	73%	58%	58%	29%	51%
56.3%	53%	54%	69%	53%	54%	55%
72.2%	77%	74%	76%	74%	61%	71%
72.7%	72%	74%	60%	77%	73%	80%
79.5%	76%	81%	82%	79%	76%	83%
49.8%	44%	57%	48%	57%	38%	55%
67.0%	73%	60%	77%	60%	64%	68%
70.7%	76%	73%	59%	74%	71%	71%
70.7%	75%	78%	61%	77%	67%	66%
68.8%	78%	73%	76%	68%	50%	68%
56.8%	58%	62%	48%	62%	60%	51%
60.8%	62%	45%	61%	65%	65%	67%
86.3%	93%	95%	79%	71%	87%	93%
57.3%	58%	62%	48%	56%	57%	63%
81.8%	90%	79%	66%	85%	78%	93%
62.2%	63%	69%	69%	59%	46%	67%
62.3%	61%	35%	63%	76%	76%	63%
49.8%	45%	39%	60%	50%	45%	60%
81.5%	97%	99%	10%	93%	97%	93%
62.3%	55%	70%	39%	70%	70%	70%
52.3%	44%	54%	64%	51%	38%	63%
64.7%	65%	67%	56%	69%	62%	69%
70.3%	73%	83%	70%	68%	60%	68%
71.0%	72%	84%	71%	73%	63%	63%
60.5%	66%	61%	63%	56%	63%	54%
73.0%	67%	75%	74%	74%	74%	74%
56.7%	51%	62%	57%	57%	54%	59%
57.0%	58%	58%	53%	61%	57%	55%
59.3%	62%	52%	77%	69%	38%	58%
66.3%	67%	64%	60%	69%	69%	69%
74.8%	78%	75%	72%	76%	59%	89%
73.3%	72%	71%	72%	73%	76%	76%
59.3%	66%	76%	47%	61%	56%	50%
64.0%	63%	65%	74%	67%	45%	70%
76.0%	83%	80%	64%	70%	77%	82%
66.7%	59%	57%	71%	71%	71%	71%