	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	2nd 70.4%	4th 65.2%	6th 61.3%	1st 70.7%	5th 62.3%	3rd 67.0%
28.8%	28%	22%	26%	36%	23%	38%
60.0%	71%	67%	42%	49%	77%	54%
48.3%	60%	54%	36%	57%	40%	43%
100.0%	100%	100%	100%	100%	100%	100%
76.3%	78%	73%	81%	76%	80%	70%
82.5%	73%	87%	85%	79%	82%	89%
72.3%	67%	72%	77%	71%	76%	71%
51.8%	53%	47%	47%	52%	47%	65%
58.2%	76%	76%	53%	73%	23%	48%
76.7%	72%	70%	66%	96%	76%	80%
65.3%	76%	70%	67%	63%	57%	59%
74.3%	76%	67%	80%	83%	63%	77%
77.8%	94%	77%	73%	84%	43%	96%
100.0%	100%	100%	100%	100%	100%	100%
70.5%	76%	70%	59%	77%	71%	70%
36.3%	48%	29%	31%	47%	26%	37%
65.5%	67%	66%	64%	60%	68%	68%
70.2%	78%	71%	52%	74%	77%	69%
61.7%	68%	65%	57%	60%	70%	50%
74.7%	86%	67%	72%	83%	75%	65%
82.2%	86%	79%	81%	96%	68%	83%
59.3%	69%	24%	52%	71%	65%	75%
91.8%	90%	91%	97%	84%	98%	91%
68.5%	73%	49%	71%	72%	74%	72%
77.8%	94%	77%	73%	84%	43%	96%
64.5%	69%	66%	74%	73%	42%	63%
56.2%	48%	46%	42%	59%	73%	69%
79.5%	83%	74%	82%	79%	77%	82%
81.8%	97%	98%	10%	98%	96%	92%
44.3%	47%	51%	41%	50%	41%	36%
27.8%	37%	20%	26%	38%	18%	28%
55.5%	62%	56%	60%	54%	55%	46%
62.8%	65%	72%	53%	78%	46%	63%
75.2%	75%	77%	77%	78%	76%	68%
79.8%	81%	78%	76%	76%	80%	88%
67.0%	67%	66%	63%	75%	68%	63%
55.8%	64%	49%	57%	64%	62%	39%
42.5%	45%	42%	38%	39%	45%	46%
56.5%	68%	52%	49%	72%	39%	59%
78.7%	81%	76%	65%	96%	76%	78%
66.8%	72%	68%	76%	67%	40%	78%
53.2%	54%	56%	46%	58%	49%	56%
58.3%	63%	67%	41%	58%	69%	52%
66.3%	66%	64%	59%	79%	63%	67%
79.7%	77%	89%	84%	67%	75%	86%
59.7%	58%	63%	61%	68%	53%	55%