	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 70.5%	5th 67.7%	4th 68.6%	2nd 70.2%	6th 65.9%	3rd 68.7%
63.7%	78%	51%	71%	63%	59%	60%
71.0%	75%	76%	69%	77%	56%	73%
77.7%	81%	85%	86%	76%	64%	74%
59.0%	59%	66%	57%	55%	56%	61%
72.7%	83%	42%	81%	83%	68%	79%
75.0%	81%	78%	79%	78%	70%	64%
81.5%	75%	75%	78%	86%	92%	83%
59.0%	66%	100%	51%	37%	56%	44%
48.0%	57%	16%	48%	59%	54%	54%
84.5%	86%	82%	85%	81%	82%	91%
64.0%	67%	65%	45%	67%	74%	66%
44.3%	45%	19%	45%	54%	50%	53%
51.5%	61%	81%	42%	61%	27%	37%
72.5%	68%	74%	79%	78%	59%	77%
52.2%	50%	60%	56%	57%	36%	54%
81.0%	89%	77%	75%	85%	79%	81%
68.3%	70%	69%	65%	71%	73%	62%
66.5%	71%	46%	63%	73%	74%	72%
78.2%	81%	81%	83%	80%	69%	75%
65.3%	67%	54%	78%	69%	56%	68%
67.7%	68%	59%	79%	74%	56%	70%
78.7%	72%	78%	86%	83%	71%	82%
54.0%	60%	80%	47%	38%	61%	38%
60.8%	66%	52%	58%	64%	63%	62%
49.0%	47%	40%	64%	56%	34%	53%
66.8%	67%	64%	81%	73%	47%	69%
90.8%	96%	88%	79%	93%	93%	96%
79.5%	88%	83%	70%	80%	82%	74%
70.3%	76%	74%	59%	72%	74%	67%
63.0%	63%	60%	58%	63%	64%	70%
35.8%	24%	81%	26%	31%	28%	25%
65.7%	66%	40%	63%	76%	70%	79%
79.3%	79%	80%	84%	80%	75%	78%
79.0%	75%	68%	89%	73%	83%	86%
53.8%	55%	67%	55%	50%	57%	39%
73.8%	81%	73%	64%	73%	71%	81%
78.7%	73%	55%	86%	85%	86%	87%
76.2%	74%	73%	83%	73%	69%	85%
72.8%	65%	75%	67%	82%	73%	75%
56.8%	55%	57%	47%	63%	56%	63%
70.2%	72%	64%	70%	72%	74%	69%
70.7%	71%	74%	68%	67%	73%	71%
81.8%	85%	68%	80%	85%	85%	88%
79.0%	92%	77%	94%	76%	68%	67%
82.8%	86%	86%	76%	87%	77%	85%
69.2%	72%	71%	70%	69%	64%	69%
69.0%	79%	73%	68%	68%	64%	62%
58.0%	64%	72%	43%	63%	48%	58%
79.2%	66%	76%	76%	83%	88%	86%
79.0%	81%	74%	87%	76%	76%	80%
63.0%	71%	56%	76%	66%	47%	62%
78.3%	73%	80%	79%	81%	83%	74%
86.5%	83%	91%	91%	77%	96%	81%
49.5%	50%	50%	48%	50%	47%	52%