	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 78.4%	1st 78.5%	6th 69.4%	3rd 77.5%	5th 74.3%	4th 74.4%
61.0%	75%	57%	62%	60%	61%	51%
89.0%	88%	88%	92%	94%	85%	87%
84.8%	89%	93%	87%	89%	73%	78%
74.2%	74%	78%	76%	77%	73%	67%
63.8%	72%	51%	55%	62%	63%	80%
71.0%	66%	78%	58%	76%	74%	74%
81.0%	87%	84%	60%	87%	89%	79%
59.5%	65%	100%	41%	44%	55%	52%
73.5%	70%	78%	66%	83%	73%	71%
70.7%	71%	76%	50%	75%	80%	72%
72.3%	67%	76%	63%	71%	78%	79%
82.3%	92%	81%	78%	80%	82%	81%
56.2%	61%	75%	58%	61%	41%	41%
83.3%	89%	84%	75%	85%	81%	86%
75.7%	83%	77%	66%	80%	75%	73%
87.5%	95%	86%	85%	90%	76%	93%
72.7%	74%	76%	66%	78%	75%	67%
78.8%	81%	88%	67%	83%	77%	77%
61.7%	70%	63%	58%	65%	53%	61%
78.0%	85%	84%	63%	83%	82%	71%
83.2%	84%	83%	83%	86%	79%	84%
79.8%	81%	82%	69%	86%	79%	82%
49.5%	56%	50%	52%	35%	64%	40%
80.8%	86%	79%	79%	86%	77%	78%
81.7%	85%	84%	77%	82%	78%	84%
91.2%	92%	93%	89%	93%	86%	94%
87.7%	87%	91%	89%	89%	84%	86%
69.3%	77%	81%	59%	70%	73%	56%
71.8%	83%	71%	53%	85%	70%	69%
72.3%	76%	81%	71%	71%	63%	72%
67.5%	73%	71%	55%	63%	71%	72%
62.7%	63%	47%	59%	66%	63%	78%
74.2%	73%	76%	50%	79%	89%	78%
79.7%	80%	77%	83%	80%	71%	87%
56.3%	57%	59%	55%	51%	59%	57%
83.7%	66%	91%	91%	86%	86%	82%
86.7%	88%	92%	76%	91%	92%	81%
57.7%	61%	44%	57%	56%	71%	57%
84.2%	85%	90%	86%	83%	80%	81%
83.0%	78%	87%	77%	84%	91%	81%
81.3%	76%	92%	81%	82%	87%	70%
73.5%	81%	79%	61%	71%	81%	68%
76.3%	84%	71%	70%	81%	71%	81%
78.5%	87%	83%	87%	84%	59%	71%
86.3%	86%	84%	83%	87%	89%	89%
70.0%	72%	73%	64%	77%	64%	70%
57.3%	68%	59%	51%	69%	37%	60%
67.7%	72%	76%	44%	74%	75%	65%
88.2%	94%	97%	76%	87%	93%	82%
78.7%	83%	83%	72%	84%	71%	79%
85.2%	90%	90%	83%	89%	66%	93%
83.8%	87%	78%	86%	91%	80%	81%
84.8%	78%	93%	79%	79%	93%	87%
81.0%	92%	79%	73%	85%	72%	85%