	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 64.6%	4th 62.8%	3rd 62.9%	1st 65.1%	6th 58.9%	5th 60.6%
60.0%	70%	59%	63%	59%	59%	50%
50.8%	61%	56%	46%	57%	39%	46%
62.7%	60%	78%	65%	56%	55%	62%
52.7%	59%	67%	52%	48%	43%	47%
69.0%	59%	63%	83%	76%	62%	71%
69.8%	82%	41%	84%	79%	70%	63%
52.5%	58%	54%	55%	50%	42%	56%
61.0%	72%	100%	50%	44%	56%	44%
54.8%	54%	88%	44%	52%	40%	51%
62.3%	71%	66%	58%	66%	59%	54%
84.8%	89%	86%	71%	91%	86%	86%
52.7%	57%	25%	57%	57%	59%	61%
56.3%	61%	79%	53%	63%	38%	44%
55.5%	53%	59%	61%	60%	38%	62%
51.0%	49%	49%	60%	59%	38%	51%
67.7%	76%	76%	63%	74%	62%	55%
62.5%	66%	55%	57%	71%	67%	59%
65.7%	72%	52%	71%	76%	54%	69%
67.8%	75%	65%	77%	74%	58%	58%
64.3%	70%	63%	66%	63%	62%	62%
73.3%	72%	64%	76%	79%	75%	74%
59.8%	61%	39%	70%	63%	56%	70%
40.8%	50%	56%	32%	26%	55%	26%
70.5%	76%	54%	71%	76%	73%	73%
57.8%	55%	42%	65%	59%	59%	67%
63.7%	67%	51%	79%	67%	48%	70%
86.2%	88%	91%	89%	79%	79%	91%
72.0%	76%	83%	62%	76%	73%	62%
68.2%	69%	81%	47%	77%	72%	63%
77.0%	58%	86%	86%	60%	86%	86%
40.8%	35%	71%	21%	46%	26%	46%
59.0%	59%	71%	52%	62%	49%	61%
51.5%	56%	55%	45%	56%	49%	48%
62.5%	66%	51%	63%	65%	63%	67%
71.7%	71%	91%	79%	71%	71%	47%
64.5%	73%	66%	60%	68%	60%	60%
73.5%	67%	61%	87%	76%	67%	83%
53.7%	55%	60%	62%	52%	61%	32%
67.8%	66%	66%	54%	75%	77%	69%
63.2%	75%	75%	60%	69%	45%	55%
57.7%	61%	51%	54%	60%	60%	60%
59.2%	50%	52%	69%	69%	54%	61%
63.8%	59%	60%	72%	66%	66%	60%
60.2%	69%	38%	85%	61%	54%	54%
90.3%	92%	91%	68%	100%	100%	91%
69.0%	54%	75%	70%	79%	86%	50%
50.5%	62%	54%	46%	59%	46%	36%
67.7%	67%	79%	70%	66%	59%	65%
81.2%	73%	69%	81%	86%	86%	92%
65.8%	61%	79%	80%	56%	44%	75%
36.0%	48%	25%	41%	41%	20%	41%
63.2%	69%	56%	64%	59%	67%	64%
48.0%	47%	56%	47%	44%	50%	44%
59.7%	67%	13%	56%	91%	55%	76%