	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 62.2%	1st 62.9%	5th 58.5%	3rd 60.6%	6th 56.4%	4th 60.1%
62.2%	67%	64%	50%	64%	64%	64%
52.3%	49%	52%	55%	56%	46%	56%
49.8%	46%	48%	55%	51%	48%	51%
48.3%	50%	38%	58%	43%	32%	69%
79.5%	76%	84%	75%	77%	82%	83%
81.5%	78%	73%	94%	84%	76%	84%
60.5%	56%	65%	63%	63%	58%	58%
39.2%	44%	44%	29%	37%	44%	37%
63.7%	58%	69%	48%	62%	70%	75%
56.7%	63%	63%	49%	57%	47%	61%
58.5%	60%	61%	64%	64%	44%	58%
47.7%	54%	51%	47%	51%	35%	48%
65.3%	66%	74%	70%	64%	54%	64%
59.0%	58%	59%	63%	58%	59%	57%
56.7%	64%	66%	57%	56%	40%	57%
66.2%	68%	71%	67%	63%	64%	64%
72.2%	82%	82%	74%	62%	63%	70%
55.8%	57%	64%	49%	55%	55%	55%
57.0%	59%	57%	45%	63%	62%	56%
53.3%	51%	58%	58%	50%	54%	49%
47.3%	55%	46%	41%	47%	52%	43%
62.7%	67%	65%	70%	60%	54%	60%
65.7%	66%	69%	63%	67%	62%	67%
63.0%	68%	70%	63%	62%	51%	64%
57.8%	51%	62%	64%	57%	62%	51%
51.8%	56%	55%	43%	52%	52%	53%
53.2%	59%	55%	42%	50%	63%	50%
60.8%	67%	79%	53%	59%	60%	47%
44.2%	62%	48%	31%	50%	31%	43%
51.8%	50%	54%	45%	64%	49%	49%
61.2%	66%	66%	66%	58%	50%	61%
88.2%	93%	91%	82%	85%	91%	87%
49.7%	46%	48%	55%	50%	48%	51%
64.0%	67%	60%	70%	66%	64%	57%
48.7%	55%	35%	43%	52%	52%	55%
69.3%	71%	77%	68%	72%	64%	64%
76.2%	86%	84%	79%	74%	58%	76%
86.8%	93%	88%	90%	90%	77%	83%
50.0%	51%	51%	44%	56%	54%	44%
70.5%	65%	67%	76%	73%	71%	71%
66.7%	67%	79%	62%	67%	54%	71%
53.2%	54%	55%	43%	58%	51%	58%
56.5%	55%	57%	51%	56%	57%	63%