	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 67.0%	2nd 65.7%	6th 59.4%	4th 62.9%	5th 61.7%	3rd 63.0%
68.3%	77%	66%	78%	66%	66%	57%
85.3%	90%	89%	77%	81%	86%	89%
83.0%	84%	87%	89%	89%	74%	75%
61.0%	64%	74%	59%	56%	57%	56%
46.2%	57%	37%	45%	45%	20%	73%
45.7%	45%	45%	37%	47%	51%	49%
72.7%	79%	79%	51%	78%	76%	73%
60.7%	75%	100%	41%	47%	60%	41%
46.0%	50%	35%	41%	48%	55%	47%
63.0%	69%	69%	47%	59%	67%	67%
72.2%	81%	69%	56%	65%	80%	82%
60.3%	60%	50%	58%	64%	62%	68%
72.7%	83%	92%	69%	75%	55%	62%
82.3%	81%	90%	74%	87%	75%	87%
74.5%	78%	75%	84%	77%	63%	70%
86.0%	82%	95%	85%	77%	96%	81%
71.0%	62%	72%	78%	75%	68%	71%
75.3%	78%	65%	76%	76%	80%	77%
60.0%	71%	63%	56%	56%	51%	63%
57.2%	58%	63%	54%	54%	60%	54%
61.2%	62%	60%	57%	60%	64%	64%
59.3%	66%	58%	52%	60%	60%	60%
59.7%	68%	61%	66%	40%	77%	46%
55.7%	59%	34%	62%	63%	55%	61%
61.3%	64%	61%	68%	60%	55%	60%
55.3%	56%	60%	64%	54%	46%	52%
69.3%	68%	70%	69%	67%	73%	69%
58.5%	67%	59%	49%	60%	58%	58%
64.0%	73%	73%	53%	73%	56%	56%
60.7%	65%	64%	61%	56%	54%	64%
53.3%	50%	56%	51%	60%	57%	46%
52.8%	66%	54%	44%	47%	41%	65%
48.8%	57%	56%	33%	42%	55%	50%
68.2%	73%	75%	58%	68%	72%	63%
45.0%	53%	51%	47%	34%	44%	41%
76.3%	65%	85%	65%	81%	81%	81%
57.2%	61%	73%	43%	59%	58%	49%
41.7%	50%	40%	41%	38%	41%	40%
59.5%	54%	66%	56%	57%	63%	61%
50.3%	49%	63%	34%	45%	60%	51%
59.2%	58%	64%	56%	60%	58%	59%
48.7%	61%	58%	33%	47%	57%	36%
59.5%	60%	63%	60%	68%	55%	51%
73.7%	79%	78%	65%	82%	60%	78%
61.8%	65%	58%	53%	67%	59%	69%
63.7%	67%	69%	63%	65%	51%	67%
48.5%	67%	52%	39%	52%	29%	52%
56.5%	65%	60%	43%	64%	60%	47%
85.3%	85%	86%	82%	89%	86%	84%
60.2%	67%	61%	65%	61%	46%	61%
84.0%	85%	80%	85%	87%	78%	89%
62.2%	54%	61%	66%	62%	64%	66%
80.8%	77%	80%	77%	77%	91%	83%
71.2%	76%	44%	90%	68%	68%	81%