	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 64.1%	2nd 65.2%	4th 62.6%	1st 65.3%	6th 58.5%	5th 60.3%
60.8%	70%	55%	70%	59%	59%	52%
40.3%	44%	33%	38%	44%	34%	49%
60.8%	60%	70%	65%	56%	55%	59%
53.2%	57%	62%	44%	52%	47%	57%
61.8%	55%	63%	63%	69%	62%	59%
75.0%	82%	82%	83%	82%	80%	41%
57.7%	58%	63%	55%	58%	56%	56%
59.3%	75%	100%	44%	44%	56%	37%
50.5%	54%	60%	46%	52%	40%	51%
63.7%	72%	62%	58%	66%	62%	62%
82.5%	81%	78%	71%	91%	91%	83%
55.7%	57%	44%	62%	57%	57%	57%
54.8%	61%	70%	53%	63%	38%	44%
54.3%	53%	55%	69%	59%	38%	52%
50.2%	42%	61%	60%	49%	38%	51%
64.5%	66%	52%	69%	74%	52%	74%
64.8%	70%	73%	49%	71%	62%	64%
72.3%	73%	85%	68%	74%	66%	68%
69.2%	65%	75%	65%	75%	58%	77%
63.8%	65%	63%	61%	63%	66%	65%
71.2%	71%	67%	79%	80%	59%	71%
56.5%	44%	59%	73%	59%	45%	59%
34.5%	38%	44%	32%	26%	41%	26%
73.5%	77%	75%	66%	76%	74%	73%
52.3%	52%	48%	65%	59%	39%	51%
67.5%	72%	70%	76%	79%	48%	60%
86.2%	80%	91%	88%	79%	86%	93%
72.2%	81%	84%	57%	76%	73%	62%
67.2%	72%	77%	44%	81%	67%	62%
72.7%	71%	74%	69%	78%	86%	58%
33.5%	27%	79%	12%	33%	4%	46%
61.7%	65%	72%	67%	58%	54%	54%
53.7%	58%	55%	46%	56%	54%	53%
61.7%	60%	51%	71%	61%	63%	64%
71.5%	72%	85%	79%	69%	71%	53%
81.7%	77%	81%	85%	82%	81%	84%
74.0%	77%	58%	78%	78%	76%	77%
57.7%	55%	51%	62%	62%	66%	50%
70.2%	71%	67%	64%	73%	77%	69%
75.2%	75%	69%	81%	76%	76%	74%
63.2%	68%	56%	61%	72%	58%	64%
58.8%	56%	54%	69%	66%	50%	58%
67.2%	67%	72%	70%	66%	66%	62%
60.2%	70%	38%	85%	67%	47%	54%
87.2%	97%	91%	78%	86%	80%	91%
70.5%	63%	86%	64%	79%	86%	45%
53.7%	62%	70%	44%	59%	36%	51%
67.2%	76%	73%	55%	66%	64%	69%
80.8%	73%	71%	76%	86%	86%	93%
58.2%	50%	66%	69%	66%	41%	57%
39.2%	44%	41%	56%	36%	23%	35%
64.3%	67%	56%	64%	63%	67%	69%
46.7%	47%	56%	47%	44%	44%	42%
58.2%	69%	29%	58%	71%	55%	67%