	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 77.2%	2nd 76.3%	6th 68.9%	3rd 75.3%	5th 69.4%	4th 73.2%
60.0%	75%	55%	64%	60%	57%	49%
83.2%	89%	84%	81%	83%	76%	86%
80.8%	85%	92%	80%	85%	69%	74%
75.7%	77%	82%	73%	69%	80%	73%
73.0%	76%	55%	77%	75%	73%	82%
80.7%	71%	85%	70%	89%	85%	84%
75.5%	78%	76%	69%	77%	76%	77%
56.5%	75%	100%	39%	37%	51%	37%
70.8%	68%	86%	60%	72%	69%	70%
87.7%	92%	93%	70%	91%	87%	93%
87.5%	87%	91%	82%	87%	91%	87%
59.5%	59%	49%	61%	62%	64%	62%
46.3%	61%	73%	10%	58%	37%	39%
83.7%	92%	85%	85%	82%	68%	90%
81.2%	88%	89%	86%	79%	60%	85%
81.8%	89%	85%	78%	86%	71%	82%
52.5%	54%	59%	50%	58%	51%	43%
75.0%	77%	81%	67%	82%	75%	68%
65.0%	78%	71%	52%	63%	54%	72%
68.3%	68%	72%	70%	68%	63%	69%
72.2%	75%	76%	87%	71%	52%	72%
87.2%	87%	93%	90%	88%	71%	94%
43.7%	49%	47%	51%	28%	53%	34%
82.7%	87%	76%	77%	83%	87%	86%
83.8%	94%	92%	86%	78%	65%	88%
73.3%	73%	75%	81%	84%	53%	74%
92.0%	91%	94%	98%	91%	88%	90%
82.5%	88%	87%	72%	85%	87%	76%
69.5%	78%	78%	57%	79%	60%	65%
72.5%	77%	75%	75%	75%	55%	78%
62.5%	64%	66%	49%	62%	72%	62%
68.0%	74%	59%	60%	72%	72%	71%
84.2%	85%	86%	63%	92%	85%	94%
77.8%	80%	80%	82%	83%	64%	78%
47.2%	55%	48%	34%	39%	59%	48%
84.7%	78%	91%	85%	88%	83%	83%
83.7%	87%	86%	74%	89%	82%	84%
61.0%	61%	59%	51%	69%	61%	65%
70.5%	68%	71%	69%	71%	71%	73%
80.3%	80%	82%	81%	82%	82%	75%
78.5%	78%	85%	73%	83%	82%	70%
79.2%	84%	82%	69%	81%	83%	76%
77.7%	80%	85%	74%	81%	73%	73%
77.0%	88%	72%	94%	83%	63%	62%
88.2%	91%	85%	76%	93%	92%	92%
78.8%	79%	86%	64%	85%	75%	84%
46.0%	63%	40%	36%	54%	32%	51%
67.0%	67%	73%	54%	72%	70%	66%
76.3%	81%	84%	67%	76%	72%	78%
63.3%	73%	64%	57%	72%	49%	65%
79.3%	85%	85%	76%	86%	63%	81%
77.0%	78%	70%	78%	79%	78%	79%
70.5%	63%	69%	74%	67%	77%	73%
79.0%	89%	54%	83%	80%	77%	91%