	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 70.4%	5th 62.9%	6th 62.0%	2nd 66.6%	4th 63.6%	3rd 64.6%
64.7%	71%	70%	58%	55%	79%	55%
54.7%	56%	33%	47%	62%	63%	67%
60.8%	62%	67%	77%	65%	49%	45%
60.2%	62%	73%	39%	64%	58%	65%
75.8%	74%	47%	82%	90%	82%	80%
58.5%	56%	61%	65%	61%	61%	47%
64.5%	65%	42%	76%	69%	72%	63%
64.8%	75%	100%	59%	37%	74%	44%
49.5%	47%	54%	40%	51%	39%	66%
64.0%	67%	51%	72%	61%	65%	68%
76.3%	91%	81%	51%	87%	70%	78%
67.7%	77%	54%	76%	67%	62%	70%
51.7%	66%	77%	41%	67%	22%	37%
77.3%	78%	73%	79%	69%	84%	81%
67.3%	66%	61%	70%	87%	52%	68%
49.2%	57%	46%	40%	60%	38%	54%
58.0%	66%	62%	44%	73%	53%	50%
60.0%	58%	72%	51%	81%	40%	58%
69.7%	71%	64%	74%	66%	66%	77%
67.5%	70%	74%	71%	61%	68%	61%
77.2%	88%	75%	82%	79%	63%	76%
65.7%	68%	35%	85%	74%	59%	73%
52.3%	60%	63%	44%	30%	79%	38%
66.5%	72%	77%	62%	66%	63%	59%
67.7%	67%	61%	76%	81%	53%	68%
65.2%	72%	62%	64%	74%	47%	72%
78.8%	87%	71%	75%	83%	83%	74%
61.5%	69%	71%	44%	60%	66%	59%
73.5%	85%	81%	51%	79%	74%	71%
86.7%	87%	94%	74%	90%	94%	81%
35.8%	32%	51%	21%	34%	22%	55%
73.0%	76%	71%	65%	79%	77%	70%
72.8%	75%	68%	75%	76%	72%	71%
69.7%	66%	68%	68%	63%	73%	80%
71.8%	79%	91%	66%	62%	79%	54%
55.8%	70%	32%	59%	57%	56%	61%
60.0%	64%	44%	57%	56%	72%	67%
77.5%	94%	79%	77%	79%	57%	79%
77.5%	73%	69%	73%	87%	85%	78%
69.7%	78%	59%	64%	57%	82%	78%
67.5%	78%	41%	68%	60%	79%	79%
49.5%	58%	59%	43%	41%	51%	45%
65.7%	76%	56%	59%	62%	64%	77%
62.3%	72%	28%	80%	67%	64%	63%
56.8%	55%	62%	51%	46%	79%	48%
85.3%	100%	71%	80%	94%	94%	73%
56.2%	79%	70%	52%	48%	39%	49%
48.7%	59%	55%	35%	46%	49%	48%
80.0%	85%	92%	76%	79%	74%	74%
53.2%	45%	61%	61%	58%	39%	55%
69.7%	77%	62%	74%	81%	56%	68%
72.3%	78%	65%	68%	73%	70%	80%
70.3%	78%	66%	60%	73%	72%	73%
52.7%	63%	27%	45%	70%	54%	57%