	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	3rd 65.8%	1st 67.3%	5th 62.1%	2nd 65.9%	6th 61.7%	4th 64.3%
25.7%	21%	32%	12%	27%	31%	31%
68.5%	68%	80%	69%	71%	67%	56%
65.8%	65%	65%	65%	70%	75%	55%
68.3%	70%	73%	65%	72%	69%	61%
67.8%	63%	76%	77%	71%	64%	56%
59.0%	71%	47%	73%	71%	33%	59%
75.5%	73%	77%	70%	80%	77%	76%
52.8%	61%	67%	41%	58%	39%	51%
75.5%	66%	86%	82%	70%	84%	65%
61.2%	68%	71%	58%	64%	40%	66%
44.3%	41%	49%	33%	50%	48%	45%
70.2%	78%	70%	61%	67%	79%	66%
58.3%	57%	56%	61%	61%	54%	61%
82.7%	83%	88%	80%	84%	73%	88%
35.5%	42%	39%	39%	23%	47%	23%
87.3%	96%	93%	88%	88%	70%	89%
73.8%	75%	78%	67%	80%	69%	74%
57.3%	70%	46%	57%	57%	57%	57%
82.2%	84%	67%	85%	97%	82%	78%
47.5%	64%	53%	39%	53%	25%	51%
78.7%	73%	85%	72%	72%	88%	82%
63.7%	56%	84%	45%	55%	72%	70%
67.0%	68%	71%	65%	66%	66%	66%
80.8%	78%	84%	75%	83%	82%	83%
33.5%	33%	31%	25%	25%	40%	47%
76.2%	78%	80%	74%	79%	76%	70%
77.8%	75%	80%	86%	70%	72%	84%
53.5%	58%	62%	49%	54%	54%	44%
67.5%	70%	79%	61%	71%	63%	61%
59.5%	71%	100%	24%	59%	73%	30%
67.5%	71%	59%	61%	79%	57%	78%
68.7%	68%	52%	72%	71%	76%	73%
66.8%	69%	71%	70%	66%	60%	65%
60.5%	69%	71%	61%	60%	44%	58%
69.5%	73%	71%	70%	68%	66%	69%
72.8%	72%	77%	64%	76%	69%	79%
51.8%	55%	40%	53%	52%	54%	57%
67.0%	59%	64%	69%	79%	56%	75%
77.8%	83%	81%	76%	81%	70%	76%
57.2%	59%	69%	45%	62%	58%	50%
78.3%	79%	64%	67%	83%	85%	92%
49.5%	56%	29%	45%	59%	45%	63%
58.5%	68%	61%	41%	65%	44%	72%
71.7%	74%	81%	63%	75%	68%	69%
58.5%	61%	59%	72%	66%	37%	56%
50.0%	55%	67%	44%	48%	41%	45%
69.8%	67%	63%	72%	75%	69%	73%
75.7%	66%	73%	78%	79%	78%	80%
41.0%	42%	42%	45%	45%	31%	41%
73.5%	78%	72%	70%	73%	71%	77%
60.0%	69%	60%	44%	68%	58%	61%
67.3%	68%	62%	82%	62%	63%	67%
73.7%	75%	73%	76%	77%	67%	74%
63.7%	70%	73%	63%	63%	57%	56%
69.3%	64%	64%	73%	76%	70%	69%
69.8%	76%	80%	54%	80%	59%	70%
63.7%	73%	61%	64%	75%	56%	53%
68.8%	70%	52%	78%	63%	75%	75%
73.2%	75%	70%	77%	75%	70%	72%
49.8%	49%	50%	43%	61%	46%	50%
74.2%	76%	86%	61%	65%	85%	72%
68.7%	69%	67%	68%	60%	74%	74%
60.5%	52%	72%	68%	60%	56%	55%
64.5%	58%	70%	66%	63%	66%	64%
76.2%	70%	78%	79%	77%	72%	81%
57.5%	58%	59%	65%	47%	58%	58%
68.2%	71%	69%	76%	65%	64%	64%
67.3%	68%	66%	69%	70%	61%	70%
81.0%	85%	72%	80%	80%	86%	83%
78.2%	75%	75%	91%	79%	77%	72%
47.5%	52%	47%	51%	46%	41%	48%
41.0%	46%	46%	33%	54%	30%	37%
54.7%	59%	60%	42%	52%	63%	52%
66.0%	59%	74%	69%	68%	64%	62%
59.3%	63%	59%	62%	59%	43%	70%
61.7%	58%	61%	57%	58%	69%	67%
58.5%	58%	59%	50%	70%	55%	59%
43.8%	29%	51%	36%	36%	55%	56%
62.3%	71%	62%	80%	58%	42%	61%
43.8%	61%	73%	10%	49%	26%	44%
60.2%	69%	100%	49%	44%	55%	44%
92.0%	91%	88%	90%	97%	90%	96%
66.5%	59%	77%	49%	62%	79%	73%
38.7%	40%	38%	40%	43%	29%	42%
52.7%	49%	46%	46%	53%	63%	59%
77.2%	79%	75%	83%	79%	74%	73%
66.0%	75%	64%	66%	71%	57%	63%
68.7%	56%	80%	62%	69%	78%	67%
81.2%	85%	92%	89%	73%	73%	75%
85.8%	76%	87%	88%	91%	84%	89%
85.2%	86%	91%	86%	88%	81%	79%