	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 66.4%	2nd 65.3%	6th 59.5%	4th 62.4%	5th 61.1%	3rd 62.7%
67.5%	68%	66%	78%	66%	66%	61%
82.2%	80%	85%	77%	81%	81%	89%
82.7%	84%	84%	89%	90%	74%	75%
57.2%	64%	62%	59%	56%	46%	56%
46.7%	56%	37%	49%	45%	20%	73%
45.5%	45%	45%	37%	43%	54%	49%
73.0%	79%	74%	60%	78%	74%	73%
60.0%	75%	100%	41%	47%	60%	37%
43.7%	50%	40%	38%	48%	39%	47%
61.2%	69%	67%	47%	54%	67%	63%
74.7%	79%	69%	56%	82%	80%	82%
60.7%	60%	48%	58%	64%	68%	66%
73.8%	83%	99%	69%	75%	55%	62%
78.8%	80%	83%	74%	74%	75%	87%
73.8%	76%	75%	84%	75%	63%	70%
80.3%	76%	95%	65%	70%	95%	81%
70.8%	62%	72%	78%	76%	68%	69%
71.5%	74%	47%	76%	76%	79%	77%
60.5%	71%	65%	56%	56%	52%	63%
57.7%	60%	64%	59%	54%	55%	54%
60.5%	62%	60%	59%	60%	61%	61%
58.5%	66%	58%	52%	60%	58%	57%
59.7%	68%	61%	66%	40%	77%	46%
56.3%	59%	35%	62%	63%	64%	55%
60.5%	66%	61%	66%	57%	55%	58%
54.2%	60%	54%	60%	55%	44%	52%
67.7%	68%	61%	69%	67%	72%	69%
59.3%	67%	63%	49%	60%	58%	59%
67.5%	72%	73%	53%	73%	67%	67%
59.0%	65%	54%	61%	54%	56%	64%
51.0%	56%	54%	51%	60%	39%	46%
49.7%	66%	46%	44%	42%	43%	57%
50.0%	57%	57%	32%	42%	56%	56%
69.7%	73%	75%	58%	78%	72%	62%
45.7%	53%	48%	47%	34%	44%	48%
82.5%	71%	90%	85%	81%	87%	81%
58.7%	67%	69%	43%	61%	56%	56%
46.2%	56%	50%	41%	40%	50%	40%
62.5%	54%	66%	63%	63%	67%	62%
48.8%	50%	63%	34%	45%	54%	47%
57.7%	61%	64%	58%	60%	45%	58%
48.2%	62%	64%	33%	40%	59%	31%
56.3%	61%	66%	63%	51%	46%	51%
74.6%		78%	65%	82%	70%	78%
60.2%	56%	57%	53%	67%	59%	69%
62.8%	62%	69%	63%	65%	51%	67%
46.0%	66%	54%	35%	52%	20%	49%
57.3%	67%	67%	43%	64%	60%	43%
86.5%	88%	90%	82%	89%	86%	84%
62.5%	67%	67%	65%	61%	54%	61%
83.5%	82%	80%	85%	87%	78%	89%
62.3%	54%	61%	66%	63%	64%	66%
80.7%	69%	91%	77%	77%	87%	83%
68.8%	76%	41%	79%	68%	68%	81%