	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 63.1%	2nd 61.1%	6th 53.5%	4th 59.8%	3rd 60.5%	5th 56.1%
50.0%	67%	59%	47%	47%	33%	47%
65.0%	68%	61%	66%	68%	73%	54%
90.7%	92%	94%	88%	94%	88%	88%
56.7%	63%	43%	52%	62%	61%	59%
53.5%	62%	42%	53%	57%	42%	65%
59.2%	61%	64%	40%	58%	76%	56%
64.8%	68%	75%	46%	70%	73%	57%
44.2%	66%	44%	44%	37%	44%	30%
51.0%	57%	41%	51%	55%	53%	49%
53.3%	61%	62%	38%	59%	52%	48%
47.8%	41%	54%	46%	49%	52%	45%
70.8%	75%	63%	75%	76%	66%	70%
58.5%	66%	80%	51%	59%	44%	51%
75.8%	78%	84%	61%	82%	76%	74%
69.2%	72%	73%	61%	73%	70%	66%
57.8%	56%	60%	60%	55%	71%	45%
67.7%	72%	68%	60%	72%	70%	64%
63.2%	65%	84%	46%	70%	56%	58%
42.8%	50%	32%	36%	44%	51%	44%
59.2%	65%	65%	44%	61%	62%	58%
73.8%	77%	76%	60%	77%	76%	77%
47.5%	53%	47%	41%	53%	49%	42%
56.3%	64%	56%	68%	41%	68%	41%
52.8%	63%	67%	43%	58%	47%	39%
75.8%	77%	71%	72%	72%	84%	79%
63.5%	63%	65%	57%	68%	66%	62%
89.2%	89%	86%	81%	100%	88%	91%
71.2%	79%	66%	63%	76%	77%	66%
57.8%	70%	73%	44%	52%	62%	46%
43.8%	59%	33%	35%	37%	54%	45%
61.2%	70%	58%	49%	64%	59%	67%
43.3%	41%	31%	44%	49%	44%	51%
55.5%	58%	56%	35%	50%	74%	60%
48.5%	51%	54%	41%	51%	51%	43%
28.3%	26%	27%	29%	27%	27%	34%
51.2%	42%	70%	66%	51%	28%	50%
60.3%	68%	69%	40%	62%	71%	52%
46.8%	48%	47%	47%	47%	45%	47%
59.8%	63%	64%	65%	54%	56%	57%
68.3%	69%	70%	76%	66%	73%	56%
59.0%	52%	68%	68%	49%	68%	49%
58.7%	63%	66%	47%	54%	75%	47%
48.2%	51%	56%	44%	44%	59%	35%
79.2%	81%	73%	91%	86%	62%	82%
40.8%	42%	48%	34%	42%	42%	37%
40.8%	53%	33%	29%	44%	45%	41%
26.0%	45%	22%	17%	24%	24%	24%
58.3%	68%	68%	36%	56%	71%	51%
84.0%	88%	94%	71%	73%	88%	90%
54.7%	60%	77%	53%	52%	43%	43%
73.0%	75%	73%	59%	78%	80%	73%
68.8%	62%	61%	76%	75%	73%	66%
82.3%	75%	82%	79%	87%	76%	95%
57.0%	58%	42%	65%	63%	51%	63%