	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 77.0%	1st 77.8%	6th 67.2%	3rd 76.2%	5th 68.9%	4th 73.8%
51.7%	46%	64%	48%	57%	45%	50%
61.8%	69%	76%	43%	58%	64%	61%
55.0%	72%	73%	38%	52%	47%	48%
98.0%	98%	98%	98%	98%	98%	98%
71.5%	69%	79%	65%	66%	66%	84%
66.2%	55%	75%	64%	55%	74%	74%
88.2%	89%	88%	89%	90%	89%	84%
68.3%	70%	79%	50%	58%	75%	78%
56.2%	51%	77%	44%	75%	40%	50%
75.5%	84%	83%	61%	84%	70%	71%
78.2%	88%	92%	75%	74%	70%	70%
71.5%	79%	76%	77%	81%	54%	62%
82.3%	82%	90%	90%	97%	54%	81%
98.0%	98%	98%	98%	98%	98%	98%
67.5%	71%	67%	52%	70%	80%	65%
63.0%	74%	71%	48%	71%	56%	58%
81.5%	81%	84%	83%	81%	78%	82%
74.3%	84%	74%	66%	77%	66%	79%
69.5%	81%	72%	53%	68%	67%	76%
65.3%	76%	73%	72%	72%	45%	54%
65.8%	67%	66%	61%	69%	63%	69%
65.3%	79%	56%	55%	62%	62%	78%
95.2%	92%	99%	99%	86%	99%	96%
78.5%	85%	63%	74%	81%	80%	88%
79.5%	74%	92%	98%	91%	48%	74%
64.8%	60%	68%	76%	77%	52%	56%
78.2%	75%	59%	72%	82%	91%	90%
76.2%	88%	73%	72%	87%	62%	75%
74.5%	86%	88%	10%	80%	93%	90%
62.7%	67%	59%	57%	61%	69%	63%
56.2%	62%	50%	49%	71%	52%	53%
72.0%	74%	80%	63%	73%	69%	73%
76.0%	82%	84%	59%	84%	75%	72%
68.5%	71%	89%	71%	64%	49%	67%
88.2%	92%	87%	95%	92%	80%	83%
84.7%	83%	86%	76%	87%	90%	86%
74.5%	75%	88%	74%	73%	74%	63%
70.2%	79%	67%	68%	78%	59%	70%
69.0%	78%	74%	55%	79%	64%	64%
72.0%	86%	75%	65%	75%	65%	66%
80.0%	82%	86%	79%	76%	76%	81%
80.2%	74%	81%	78%	83%	80%	85%
56.5%	60%	74%	36%	53%	54%	62%
71.2%	71%	71%	55%	81%	67%	82%
93.2%	91%	94%	97%	92%	87%	98%
84.5%	93%	80%	85%	85%	75%	89%