	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%	2nd 67.3%	5th 63.5%	3rd 66.7%	6th 61.0%	4th 64.6%
59.5%	66%	65%	46%	59%	66%	55%
46.7%	48%	67%	27%	45%	49%	44%
78.2%	75%	61%	86%	78%	84%	85%
68.5%	68%	66%	73%	68%	68%	68%
49.2%	58%	56%	52%	48%	31%	50%
82.0%	73%	87%	72%	87%	89%	84%
67.0%	80%	78%	52%	81%	49%	62%
67.3%	72%	69%	73%	48%	71%	71%
68.8%	77%	72%	71%	55%	66%	72%
68.3%	59%	69%	79%	66%	66%	71%
78.5%	84%	56%	84%	84%	78%	85%
61.3%	69%	67%	70%	66%	37%	59%
66.5%	66%	65%	64%	65%	68%	71%
79.3%	98%	82%	76%	89%	55%	76%
53.8%	67%	34%	62%	54%	57%	49%
47.3%	46%	76%	36%	51%	37%	38%
44.2%	44%	43%	45%	45%	41%	47%
60.5%	64%	60%	60%	67%	55%	57%
63.7%	64%	64%	65%	64%	60%	65%
73.8%	81%	70%	52%	90%	69%	81%
87.0%	91%	100%	80%	74%	84%	93%
75.8%	70%	80%	81%	79%	66%	79%
69.2%	71%	64%	65%	70%	73%	72%
35.3%	46%	64%	26%	19%	34%	23%
58.2%	52%	87%	67%	46%	52%	45%
68.7%	78%	68%	71%	61%	61%	73%
64.7%	59%	70%	68%	63%	66%	62%
69.0%	76%	75%	49%	70%	78%	66%
60.5%	65%	65%	48%	63%	63%	59%
67.0%	65%	70%	59%	65%	72%	71%
70.3%	67%	67%	75%	70%	70%	73%
67.8%	73%	58%	70%	70%	67%	69%
66.2%	73%	66%	62%	78%	59%	59%
52.0%	52%	69%	54%	55%	44%	38%
73.5%	88%	78%	70%	64%	68%	73%
85.2%	84%	79%	89%	85%	80%	94%
69.5%	66%	72%	69%	72%	65%	73%
65.2%	59%	79%	52%	75%	64%	62%
57.8%	57%	56%	58%	59%	59%	58%
58.8%	51%	53%	57%	70%	57%	65%
73.8%	76%	70%	75%	95%	64%	63%
55.0%	57%	45%	70%	56%	51%	51%
55.5%	61%	45%	54%	63%	59%	51%
60.2%	67%	75%	60%	37%	61%	61%
70.8%	76%	77%	75%	62%	63%	72%
80.3%	70%	96%	83%	96%	58%	79%
57.5%	63%	72%	53%	52%	59%	46%
90.0%	86%	99%	96%	86%	93%	80%
69.7%	72%	75%	69%	74%	54%	74%
72.5%	74%	72%	70%	72%	69%	78%
65.7%	70%	66%	56%	67%	74%	61%
46.3%	50%	44%	49%	48%	37%	50%
55.2%	57%	70%	46%	57%	54%	47%
67.7%	68%	90%	57%	65%	68%	58%
81.0%	81%	78%	80%	91%	79%	77%
77.5%	79%	93%	72%	77%	77%	67%
42.3%	36%	53%	37%	36%	36%	56%
67.5%	68%	76%	63%	59%	66%	73%
44.8%	49%	65%	34%	49%	37%	35%
67.0%	68%	65%	75%	65%	66%	63%
72.7%	75%	63%	72%	67%	82%	77%
63.7%	71%	70%	46%	64%	65%	66%
79.7%	86%	75%	86%	82%	69%	80%
53.5%	54%	51%	50%	61%	51%	54%
75.7%	76%	36%	87%	87%	79%	89%
67.3%	73%	75%	67%	78%	50%	61%
55.8%	70%	72%	38%	59%	50%	46%
70.0%	78%	81%	73%	72%	54%	62%
69.2%	63%	67%	63%	76%	77%	69%
83.0%	86%	93%	84%	71%	82%	82%
64.5%	65%	66%	74%	59%	58%	65%
72.8%	79%	41%	86%	80%	74%	77%
87.3%	97%	86%	75%	93%	93%	80%
42.3%	55%	48%	54%	37%	27%	33%
58.7%	68%	64%	58%	58%	47%	57%
81.5%	79%	64%	90%	86%	79%	91%
66.5%	79%	61%	74%	66%	53%	66%
56.0%	53%	70%	46%	54%	53%	60%
69.2%	75%	37%	80%	73%	70%	80%
77.3%	80%	73%	79%	81%	62%	89%
67.8%	72%	73%	75%	59%	59%	69%
62.2%	64%	61%	71%	75%	38%	64%
61.8%	65%	65%	53%	63%	63%	62%
78.5%	80%	79%	85%	76%	73%	78%
71.2%	68%	68%	74%	76%	65%	76%
49.8%	53%	47%	48%	60%	43%	48%
46.7%	42%	57%	55%	53%	32%	41%
55.5%	59%	61%	54%	51%	51%	57%
50.7%	55%	72%	60%	54%	23%	40%
82.3%	93%	78%	75%	90%	68%	90%
86.0%	86%	91%	72%	91%	87%	89%
52.8%	76%	70%	32%	67%	33%	39%
57.8%	60%	39%	63%	55%	55%	75%
63.5%	66%	65%	53%	65%	70%	62%
47.3%	48%	54%	55%	40%	43%	44%
67.7%	71%	66%	68%	67%	65%	69%
70.0%	67%	61%	72%	64%	75%	81%
75.0%	66%	59%	83%	82%	81%	79%
62.7%	70%	71%	43%	70%	63%	59%
49.5%	54%	69%	39%	56%	29%	50%
45.0%	54%	29%	54%	52%	41%	40%
73.8%	76%	72%	58%	79%	83%	75%
58.0%	66%	56%	55%	62%	56%	53%
60.8%	60%	62%	52%	62%	69%	60%
61.7%	63%	61%	63%	63%	49%	71%
75.5%	83%	66%	56%	89%	86%	73%
76.3%	78%	87%	70%	100%	64%	59%
59.3%	69%	80%	32%	71%	53%	51%
65.3%	60%	69%	77%	60%	49%	77%
68.2%	71%	75%	63%	75%	65%	60%
70.2%	62%	68%	74%	69%	75%	73%
54.8%	59%	55%	43%	57%	58%	57%
50.2%	44%	61%	50%	47%	61%	38%
71.0%	79%	59%	72%	78%	69%	69%
65.0%	52%	85%	70%	70%	43%	70%
67.3%	69%	71%	76%	59%	61%	68%