	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	1st 61.0%	2nd 59.6%	3rd 59.2%	4th 57.5%	6th 56.1%	5th 56.7%
47.2%	71%	43%	55%	45%	29%	40%
69.7%	76%	66%	62%	77%	66%	71%
79.7%	79%	90%	95%	88%	51%	75%
53.0%	46%	48%	55%	54%	57%	58%
42.2%	47%	13%	64%	46%	46%	37%
41.3%	44%	37%	47%	27%	37%	56%
78.2%	83%	73%	80%	82%	77%	74%
60.7%	72%	100%	59%	30%	59%	44%
71.2%	73%	58%	64%	79%	73%	80%
60.0%	67%	64%	52%	62%	59%	56%
40.8%	42%	54%	23%	44%	42%	40%
73.7%	63%	68%	68%	79%	79%	85%
48.0%	63%	77%	41%	59%	18%	30%
56.2%	56%	56%	56%	53%	59%	57%
55.8%	68%	37%	65%	49%	61%	55%
65.8%	70%	70%	59%	66%	66%	64%
50.8%	54%	51%	47%	54%	50%	49%
62.8%	66%	63%	66%	65%	51%	66%
64.5%	67%	57%	65%	67%	74%	57%
72.5%	82%	73%	75%	70%	69%	66%
57.0%	58%	60%	61%	61%	42%	60%
56.2%	63%	52%	52%	62%	56%	52%
72.8%	77%	77%	68%	59%	97%	59%
53.3%	52%	41%	62%	52%	55%	58%
52.0%	57%	46%	58%	46%	49%	56%
80.5%	85%	81%	90%	85%	57%	85%
56.7%	57%	55%	77%	50%	51%	50%
51.5%	58%	55%	49%	48%	51%	48%
56.7%	60%	53%	55%	53%	64%	55%
68.3%	66%	70%	67%	73%	71%	63%
40.7%	32%	51%	39%	44%	39%	39%
41.5%	38%	43%	33%	47%	48%	40%
58.7%	64%	63%	49%	63%	58%	55%
65.3%	67%	60%	73%	64%	58%	70%
41.7%	51%	59%	48%	44%	18%	30%
63.2%	57%	65%	70%	65%	63%	59%
65.7%	68%	59%	66%	69%	69%	63%
50.7%	38%	64%	44%	40%	77%	41%
45.7%	46%	49%	53%	42%	41%	43%
63.7%	64%	63%	64%	63%	66%	62%
47.8%	49%	37%	51%	49%	49%	52%
53.2%	56%	61%	44%	52%	58%	48%
38.2%	44%	54%	28%	34%	35%	34%
35.5%	46%	24%	59%	23%	37%	24%
62.2%	72%	65%	66%	54%	53%	63%
68.5%	59%	72%	62%	72%	72%	74%
47.7%	70%	58%	40%	44%	35%	39%
61.0%	61%	64%	55%	61%	64%	61%
63.3%	64%	69%	64%	66%	62%	55%
65.0%	56%	77%	75%	66%	42%	74%
66.0%	69%	70%	62%	69%	56%	70%
64.5%	60%	59%	68%	60%	71%	69%
90.8%	89%	95%	91%	83%	92%	95%
51.7%	51%	50%	57%	48%	50%	54%