	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 74.5%	1st 75.4%	6th 66.2%	3rd 73.2%	4th 71.8%	5th 70.4%
75.8%	83%	81%	58%	78%	86%	69%
62.3%	62%	59%	63%	66%	62%	62%
80.2%	78%	72%	82%	78%	93%	78%
65.7%	74%	58%	49%	72%	74%	67%
82.0%	83%	80%	90%	81%	73%	85%
80.8%	95%	91%	74%	82%	71%	72%
63.8%	58%	74%	54%	60%	82%	55%
71.3%	64%	88%	42%	73%	88%	73%
76.7%	74%	83%	67%	73%	86%	77%
58.2%	68%	58%	48%	62%	52%	61%
75.2%	74%	71%	91%	86%	67%	62%
50.8%	60%	59%	58%	41%	38%	49%
80.3%	83%	81%	75%	87%	67%	89%
85.8%	84%	92%	83%	90%	84%	82%
82.8%	82%	87%	77%	90%	73%	88%
67.5%	70%	71%	57%	68%	71%	68%
79.2%	87%	83%	74%	82%	77%	72%
47.5%	58%	52%	27%	51%	57%	40%
50.3%	52%	53%	37%	55%	50%	55%
61.8%	49%	66%	64%	59%	75%	58%
73.0%	78%	77%	55%	72%	84%	72%
78.7%	82%	88%	65%	82%	76%	79%
67.0%	71%	76%	73%	63%	56%	63%
79.2%	81%	86%	75%	83%	67%	83%
80.2%	86%	83%	72%	86%	71%	83%
68.5%	70%	70%	64%	73%	66%	68%
55.5%	62%	66%	39%	49%	69%	48%
81.0%	90%	89%	61%	86%	83%	77%
51.2%	72%	52%	49%	47%	31%	56%
65.7%	63%	72%	60%	70%	70%	59%
81.2%	89%	82%	78%	82%	76%	80%
75.0%	77%	83%	73%	77%	64%	76%
89.3%	87%	81%	91%	92%	98%	87%
61.0%	49%	81%	59%	53%	73%	51%
63.0%	78%	64%	47%	68%	55%	66%
66.3%	69%	56%	77%	64%	69%	63%
83.3%	87%	89%	79%	83%	79%	83%
88.3%	88%	95%	90%	92%	77%	88%
79.0%	80%	88%	71%	80%	82%	73%
67.3%	64%	64%	68%	64%	79%	65%
77.8%	77%	81%	76%	81%	76%	76%
81.2%	84%	84%	79%	80%	79%	81%
82.0%	80%	78%	76%	85%	83%	90%