	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 66.5%	4th 64.5%	5th 63.0%	1st 67.8%	6th 61.7%	2nd 66.9%
69.0%	72%	68%	65%	74%	61%	74%
71.5%	69%	78%	63%	74%	70%	75%
57.7%	68%	62%	53%	57%	53%	53%
80.5%	81%	78%	71%	78%	93%	82%
67.3%	72%	70%	68%	71%	57%	66%
58.8%	58%	59%	58%	59%	60%	59%
70.7%	70%	72%	73%	73%	68%	68%
40.2%	42%	68%	27%	33%	38%	33%
82.2%	85%	72%	82%	82%	81%	91%
68.2%	75%	76%	66%	63%	67%	62%
56.2%	59%	72%	60%	60%	30%	56%
55.5%	48%	56%	63%	58%	45%	63%
76.0%	100%	79%	60%	85%	54%	78%
79.3%	81%	83%	71%	78%	81%	82%
47.7%	42%	47%	44%	51%	51%	51%
61.0%	61%	59%	52%	63%	65%	66%
63.5%	56%	66%	65%	65%	64%	65%
71.8%	73%	66%	72%	71%	73%	76%
65.3%	62%	50%	66%	69%	72%	73%
44.7%	44%	46%	58%	54%	25%	41%
58.8%	51%	48%	79%	55%	58%	62%
59.8%	67%	26%	66%	58%	73%	69%
95.2%	94%	99%	93%	94%	97%	94%
67.8%	74%	71%	62%	71%	58%	71%
78.7%	94%	84%	65%	90%	58%	81%
43.8%	36%	45%	57%	53%	27%	45%
47.5%	36%	23%	54%	53%	57%	62%
49.2%	44%	39%	57%	62%	40%	53%
79.2%	91%	89%	45%	88%	80%	82%
73.0%	76%	77%	56%	75%	81%	73%
60.7%	58%	52%	58%	65%	62%	69%
55.7%	57%	59%	55%	56%	51%	56%
66.3%	68%	73%	62%	69%	64%	62%
86.5%	95%	68%	88%	90%	91%	87%
79.5%	85%	82%	74%	79%	82%	75%
38.5%	39%	42%	28%	42%	40%	40%
64.7%	65%	64%	68%	67%	64%	60%
67.3%	70%	56%	68%	63%	71%	76%
49.3%	46%	51%	54%	58%	36%	51%
67.2%	73%	72%	62%	69%	53%	74%
77.5%	69%	80%	86%	89%	60%	81%
73.3%	74%	70%	73%	75%	68%	80%
66.8%	71%	76%	49%	73%	71%	61%
56.7%	53%	55%	56%	63%	50%	63%
69.2%	70%	67%	71%	75%	62%	70%
73.2%	83%	73%	75%	69%	74%	65%