	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 61.7%	2nd 60.3%	3rd 58.8%	4th 57.1%	6th 55.9%	5th 56.9%
49.7%	71%	48%	55%	45%	39%	40%
68.7%	77%	66%	62%	70%	66%	71%
77.7%	79%	84%	95%	88%	45%	75%
55.0%	54%	53%	55%	53%	57%	58%
43.2%	47%	13%	64%	37%	47%	51%
35.8%	50%	27%	47%	27%	37%	27%
79.0%	80%	73%	80%	82%	77%	82%
59.3%	72%	100%	59%	37%	44%	44%
72.3%	73%	64%	65%	81%	70%	81%
59.0%	67%	56%	52%	64%	59%	56%
40.3%	46%	49%	23%	54%	33%	37%
72.7%	60%	68%	68%	76%	79%	85%
49.7%	63%	77%	37%	59%	18%	44%
56.2%	57%	56%	58%	51%	59%	56%
56.8%	68%	42%	65%	52%	61%	53%
67.0%	70%	70%	59%	73%	66%	64%
52.0%	50%	56%	43%	54%	60%	49%
65.0%	66%	63%	66%	65%	64%	66%
67.3%	67%	74%	65%	62%	74%	62%
72.7%	82%	73%	75%	73%	69%	64%
57.5%	58%	63%	61%	61%	42%	60%
55.0%	62%	52%	52%	56%	56%	52%
72.0%	77%	77%	68%	59%	92%	59%
56.5%	52%	56%	62%	56%	55%	58%
51.7%	57%	49%	56%	48%	49%	51%
81.0%	86%	84%	80%	100%	57%	79%
56.2%	57%	50%	77%	50%	51%	52%
51.7%	58%	56%	49%	48%	51%	48%
55.8%	60%	55%	51%	50%	64%	55%
67.2%	66%	72%	69%	62%	71%	63%
48.5%	32%	61%	39%	39%	55%	65%
41.0%	38%	43%	33%	47%	45%	40%
56.2%	66%	49%	49%	60%	58%	55%
64.3%	67%	64%	76%	58%	58%	63%
36.5%	51%	51%	44%	30%	13%	30%
63.8%	58%	65%	70%	66%	65%	59%
67.5%	68%	59%	66%	69%	69%	74%
47.3%	38%	64%	44%	43%	54%	41%
43.3%	46%	45%	44%	39%	43%	43%
62.8%	64%	63%	64%	62%	63%	61%
51.3%	49%	51%	51%	56%	49%	52%
53.7%	59%	61%	44%	52%	58%	48%
35.7%	38%	54%	30%	32%	35%	25%
36.2%	46%	28%	59%	24%	36%	24%
61.7%	72%	65%	66%	54%	50%	63%
73.2%	72%	89%	62%	70%	72%	74%
47.0%	65%	54%	40%	44%	35%	44%
62.3%	69%	63%	55%	61%	64%	62%
66.0%	71%	69%	64%	66%	71%	55%
61.7%	56%	67%	75%	56%	42%	74%
66.5%	69%	70%	62%	69%	59%	70%
65.3%	60%	59%	74%	60%	70%	69%
88.3%	89%	92%	91%	83%	92%	83%
51.7%	55%	46%	57%	48%	50%	54%