	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 68.7%	1st 70.5%	6th 61.8%	3rd 68.3%	5th 62.1%	4th 66.6%
71.3%	70%	72%	63%	74%	76%	73%
71.2%	63%	73%	74%	72%	73%	72%
71.0%	70%	68%	70%	76%	72%	70%
59.5%	54%	69%	54%	65%	47%	68%
94.0%	94%	91%	94%	97%	94%	94%
56.2%	65%	68%	47%	53%	51%	53%
77.3%	69%	86%	87%	76%	76%	70%
54.3%	49%	70%	32%	52%	70%	53%
81.2%	80%	80%	76%	81%	85%	85%
56.5%	62%	65%	59%	60%	30%	63%
88.0%	90%	90%	89%	92%	81%	86%
40.3%	45%	49%	33%	43%	26%	46%
76.3%	82%	80%	76%	83%	54%	83%
73.2%	78%	65%	76%	78%	62%	80%
66.3%	75%	63%	60%	65%	65%	70%
65.0%	67%	70%	52%	70%	67%	64%
54.8%	71%	69%	45%	51%	40%	53%
55.3%	64%	64%	35%	53%	63%	53%
64.0%	63%	67%	53%	72%	66%	63%
77.8%	63%	87%	86%	80%	75%	76%
74.0%	84%	75%	58%	83%	72%	72%
67.3%	77%	77%	52%	66%	63%	69%
65.7%	68%	74%	71%	79%	30%	72%
73.8%	82%	81%	67%	71%	67%	75%
69.7%	71%	68%	75%	70%	66%	68%
70.0%	68%	67%	67%	76%	63%	79%
52.0%	55%	58%	38%	54%	56%	51%
49.8%	61%	55%	38%	42%	58%	45%
45.0%	53%	48%	39%	54%	21%	55%
59.0%	58%	70%	59%	64%	53%	50%
57.0%	61%	54%	49%	59%	63%	56%
63.2%	64%	66%	64%	59%	62%	64%
53.8%	53%	51%	53%	58%	55%	53%
64.3%	56%	80%	73%	62%	60%	55%
65.2%	73%	62%	61%	68%	51%	76%
63.5%	72%	67%	56%	65%	62%	59%
65.2%	75%	52%	53%	64%	75%	72%
84.5%	90%	89%	93%	90%	75%	70%
43.0%	47%	53%	30%	42%	44%	42%
97.3%	98%	98%	98%	97%	95%	98%
62.7%	64%	74%	60%	64%	62%	52%
81.2%	78%	92%	76%	80%	78%	83%
72.0%	73%	73%	66%	78%	68%	74%