	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 67.7%	4th 63.4%	6th 61.3%	2nd 64.8%	5th 61.6%	3rd 63.6%
40.8%	22%	72%	32%	45%	34%	40%
65.2%	66%	64%	66%	65%	65%	65%
72.2%	76%	60%	72%	76%	72%	77%
55.3%	59%	58%	38%	57%	58%	62%
76.8%	75%	82%	70%	75%	83%	76%
63.2%	74%	51%	79%	65%	62%	48%
53.0%	64%	37%	51%	69%	49%	48%
59.3%	59%	63%	49%	63%	63%	59%
59.7%	59%	71%	10%	61%	96%	61%
67.2%	75%	77%	77%	57%	57%	60%
57.8%	53%	69%	51%	48%	74%	52%
68.3%	71%	82%	65%	53%	82%	57%
81.2%	86%	83%	100%	77%	57%	84%
81.8%	88%	75%	87%	79%	83%	79%
66.0%	78%	91%	64%	55%	57%	51%
50.5%	61%	59%	10%	63%	51%	59%
57.7%	63%	54%	54%	40%	64%	71%
64.3%	76%	72%	70%	60%	47%	61%
59.8%	63%	50%	65%	67%	57%	57%
71.2%	79%	70%	68%	70%	70%	70%
75.0%	66%	73%	76%	74%	80%	81%
53.3%	59%	44%	47%	59%	57%	54%
55.7%	57%	73%	51%	49%	55%	49%
73.2%	83%	51%	84%	74%	73%	74%
43.8%	29%	54%	53%	40%	39%	48%
59.0%	64%	53%	55%	55%	59%	68%
68.2%	78%	61%	51%	81%	60%	78%
72.3%	71%	75%	53%	79%	74%	82%
69.3%	70%	67%	69%	73%	64%	73%
58.2%	87%	100%	30%	44%	33%	55%
72.3%	76%	69%	59%	77%	77%	76%
58.3%	70%	40%	62%	58%	62%	58%
75.0%	74%	76%	76%	85%	60%	79%
73.5%	76%	73%	75%	75%	60%	82%
40.7%	44%	43%	44%	44%	25%	44%
53.3%	56%	46%	43%	56%	62%	57%
53.3%	56%	39%	56%	58%	57%	54%
61.2%	73%	65%	71%	55%	40%	63%
76.2%	84%	84%	79%	75%	63%	72%
54.3%	58%	70%	27%	58%	80%	33%
62.2%	63%	59%	47%	73%	61%	70%
56.2%	53%	32%	67%	67%	70%	48%
79.8%	79%	77%	80%	85%	70%	88%
52.0%	61%	63%	37%	55%	49%	47%
61.0%	59%	50%	70%	70%	52%	65%
59.5%	58%	81%	44%	77%	41%	56%
69.8%	75%	79%	77%	62%	64%	62%
56.3%	58%	52%	58%	58%	54%	58%
74.0%	79%	69%	74%	74%	64%	84%
59.7%	66%	27%	70%	65%	49%	81%
57.8%	59%	70%	45%	51%	63%	59%
75.3%	80%	76%	81%	75%	65%	75%
66.8%	68%	52%	69%	74%	67%	71%
55.3%	55%	53%	56%	56%	54%	58%
71.5%	76%	70%	75%	73%	71%	64%
60.0%	70%	50%	50%	76%	47%	67%
74.8%	76%	76%	72%	80%	69%	76%
65.0%	75%	55%	61%	75%	71%	53%
54.3%	69%	40%	51%	55%	57%	54%
52.3%	62%	52%	41%	63%	45%	51%
53.3%	70%	80%	30%	41%	64%	35%
61.7%	54%	59%	64%	66%	62%	65%
71.0%	69%	50%	82%	69%	72%	84%
68.5%	81%	42%	70%	70%	69%	79%
67.3%	65%	49%	75%	69%	80%	66%
63.0%	71%	42%	72%	64%	68%	61%
69.2%	62%	68%	77%	62%	71%	75%
70.8%	75%	79%	62%	64%	78%	67%
65.8%	67%	56%	72%	77%	70%	53%
69.8%	81%	38%	76%	71%	68%	85%
69.3%	77%	71%	73%	73%	49%	73%
66.7%	70%	66%	67%	62%	66%	69%
31.3%	30%	58%	23%	35%	25%	17%
50.3%	53%	53%	44%	51%	50%	51%
84.7%	100%	77%	86%	92%	77%	76%
72.0%	71%	67%	68%	74%	75%	77%
70.0%	70%	70%	70%	70%	70%	70%
76.7%	64%	78%	81%	80%	84%	73%
67.5%	70%	71%	56%	65%	73%	70%
67.5%	81%	89%	50%	89%	38%	58%
61.2%	69%	100%	51%	44%	59%	44%
66.0%	70%	70%	67%	67%	60%	62%
42.5%	48%	37%	32%	48%	47%	43%
52.5%	55%	50%	56%	54%	45%	55%
68.7%	73%	67%	64%	72%	63%	73%
53.8%	63%	49%	49%	55%	57%	50%
63.7%	69%	64%	70%	51%	63%	65%
71.2%	70%	59%	73%	70%	78%	77%
81.8%	92%	77%	91%	85%	71%	75%
75.0%	71%	78%	92%	63%	75%	71%
65.8%	80%	73%	73%	69%	36%	64%