	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 74.8%	1st 75.8%	6th 66.1%	3rd 73.6%	5th 70.6%	4th 71.2%
80.3%	83%	90%	58%	87%	86%	78%
64.2%	61%	59%	65%	68%	67%	65%
80.2%	78%	72%	82%	78%	93%	78%
68.8%	74%	74%	60%	72%	59%	74%
81.2%	83%	79%	84%	77%	85%	79%
81.7%	96%	91%	74%	79%	78%	72%
62.5%	58%	74%	54%	60%	74%	55%
73.2%	64%	88%	42%	73%	94%	78%
75.5%	74%	76%	67%	73%	86%	77%
57.3%	68%	61%	48%	60%	52%	55%
74.0%	74%	71%	91%	84%	57%	67%
51.8%	60%	54%	46%	51%	50%	50%
81.2%	87%	81%	75%	87%	68%	89%
81.7%	84%	92%	83%	90%	59%	82%
85.7%	82%	90%	87%	90%	78%	87%
66.8%	70%	73%	56%	66%	74%	62%
78.7%	87%	83%	74%	80%	76%	72%
47.7%	59%	53%	27%	46%	61%	40%
50.8%	56%	59%	37%	53%	45%	55%
56.2%	49%	70%	64%	59%	37%	58%
72.8%	76%	78%	55%	77%	79%	72%
78.7%	82%	88%	65%	82%	76%	79%
65.7%	71%	70%	71%	67%	52%	63%
78.8%	81%	86%	74%	82%	67%	83%
79.3%	86%	75%	77%	86%	69%	83%
67.2%	68%	70%	64%	69%	61%	71%
56.7%	62%	66%	39%	50%	69%	54%
81.3%	90%	94%	61%	89%	83%	71%
51.2%	72%	49%	48%	55%	35%	48%
65.8%	63%	73%	58%	68%	73%	60%
80.3%	89%	81%	78%	82%	72%	80%
74.7%	77%	83%	73%	77%	62%	76%
88.5%	87%	81%	91%	87%	98%	87%
61.2%	49%	81%	49%	56%	79%	53%
64.5%	76%	64%	47%	68%	55%	77%
67.2%	69%	60%	79%	66%	64%	65%
85.2%	92%	89%	79%	84%	79%	88%
89.2%	88%	95%	90%	93%	76%	93%
80.5%	84%	81%	71%	81%	85%	81%
67.3%	64%	64%	68%	64%	79%	65%
78.3%	80%	81%	76%	81%	76%	76%
81.5%	84%	84%	79%	83%	85%	74%
82.0%	80%	78%	76%	85%	83%	90%