	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 77.3%	5th 72.8%	6th 71.4%	1st 77.8%	4th 73.4%	3rd 75.4%
79.7%	87%	71%	69%	81%	83%	87%
70.8%	63%	51%	73%	81%	82%	75%
51.2%	50%	44%	57%	61%	44%	51%
81.8%	82%	86%	76%	89%	87%	71%
86.2%	85%	95%	76%	88%	86%	87%
85.3%	84%	86%	85%	85%	85%	87%
84.0%	81%	87%	85%	89%	79%	83%
69.7%	76%	66%	54%	74%	74%	74%
72.2%	69%	82%	60%	80%	70%	72%
82.7%	86%	82%	81%	84%	86%	77%
70.8%	77%	64%	83%	69%	80%	52%
74.3%	79%	76%	78%	73%	68%	72%
73.3%	80%	81%	68%	82%	60%	69%
76.0%	74%	75%	72%	79%	78%	78%
75.7%	81%	75%	75%	82%	66%	75%
82.2%	81%	78%	78%	81%	92%	83%
78.3%	75%	73%	80%	87%	78%	77%
57.5%	67%	69%	35%	57%	59%	58%
39.5%	32%	52%	36%	38%	38%	41%
76.7%	62%	78%	80%	76%	88%	76%
73.0%	76%	78%	69%	73%	71%	71%
69.0%	80%	74%	63%	71%	59%	67%
67.3%	56%	65%	73%	59%	76%	75%
76.3%	84%	70%	87%	91%	54%	72%
86.7%	90%	85%	82%	86%	83%	94%
75.0%	79%	79%	68%	79%	75%	70%
59.3%	71%	60%	38%	53%	70%	64%
72.8%	79%	71%	63%	79%	72%	73%
71.2%	82%	79%	60%	73%	73%	60%
75.0%	84%	71%	65%	82%	69%	79%
76.5%	73%	77%	81%	81%	65%	82%
91.7%	91%	98%	86%	86%	98%	91%
63.8%	62%	55%	70%	74%	59%	63%
75.0%	84%	75%	74%	78%	66%	73%
75.2%	84%	40%	78%	88%	80%	81%
59.2%	68%	50%	59%	63%	54%	61%
84.5%	82%	100%	90%	86%	63%	86%
86.3%	87%	88%	87%	86%	82%	88%
80.0%	83%	60%	82%	82%	84%	89%
93.7%	95%	89%	96%	96%	89%	97%
72.3%	79%	62%	71%	62%	81%	79%
77.8%	88%	71%	60%	88%	72%	88%
81.8%	94%	61%	69%	94%	80%	93%