	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 76.0%	5th 71.5%	6th 70.7%	1st 76.6%	4th 73.4%	3rd 74.5%
76.8%	82%	55%	69%	86%	83%	86%
66.2%	63%	28%	68%	82%	81%	75%
51.3%	50%	44%	57%	59%	47%	51%
79.5%	81%	81%	82%	76%	86%	71%
84.8%	91%	86%	75%	87%	82%	88%
85.5%	85%	91%	91%	85%	77%	84%
86.5%	88%	75%	88%	86%	91%	91%
71.0%	78%	77%	50%	74%	74%	73%
70.0%	69%	72%	53%	80%	70%	76%
82.7%	79%	86%	86%	81%	78%	86%
72.7%	79%	64%	84%	72%	74%	63%
71.3%	73%	70%	72%	73%	68%	72%
74.8%	74%	84%	80%	77%	58%	76%
76.2%	80%	81%	70%	78%	70%	78%
74.7%	71%	77%	74%	78%	70%	78%
82.3%	81%	63%	82%	88%	92%	88%
80.7%	81%	82%	75%	87%	76%	83%
61.0%	67%	83%	44%	59%	59%	54%
39.8%	34%	57%	34%	38%	35%	41%
72.7%	80%	82%	64%	77%	67%	66%
72.2%	75%	70%	67%	80%	68%	73%
70.0%	77%	78%	61%	66%	72%	66%
65.7%	54%	72%	75%	56%	63%	74%
66.7%	70%	57%	69%	83%	51%	70%
79.3%	87%	83%	75%	78%	75%	78%
78.2%	79%	84%	78%	79%	75%	74%
64.8%	74%	84%	51%	53%	63%	64%
71.5%	76%	69%	60%	74%	77%	73%
62.8%	77%	69%	59%	62%	66%	44%
74.3%	84%	74%	66%	74%	77%	71%
69.7%	71%	38%	77%	81%	72%	79%
93.3%	95%	98%	86%	89%	98%	94%
63.3%	59%	55%	70%	74%	59%	63%
66.7%	68%	73%	58%	67%	67%	67%
65.0%	84%	34%	61%	63%	76%	72%
62.3%	61%	51%	72%	68%	61%	61%
82.5%	72%	87%	83%	87%	81%	85%
86.5%	88%	95%	87%	86%	75%	88%
81.0%	83%	64%	74%	95%	90%	80%
94.0%	92%	89%	96%	98%	92%	97%
73.8%	75%	59%	72%	76%	81%	80%
81.2%	88%	79%	60%	88%	88%	84%
86.2%	91%	73%	83%	94%	91%	85%