	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	3rd 77.3%	1st 77.9%	6th 70.6%	2nd 77.7%	5th 74.7%	4th 75.3%
46.7%	46%	64%	37%	42%	38%	53%
74.3%	74%	87%	69%	76%	74%	66%
75.0%	68%	81%	67%	83%	84%	67%
70.3%	76%	73%	48%	79%	77%	69%
78.2%	74%	97%	98%	77%	58%	65%
78.8%	88%	77%	84%	84%	69%	71%
80.8%	81%	72%	81%	84%	89%	78%
74.7%	83%	82%	66%	72%	69%	76%
67.5%	65%	63%	73%	62%	80%	62%
73.8%	83%	74%	68%	75%	56%	87%
74.8%	66%	77%	62%	77%	84%	83%
76.7%	93%	78%	63%	76%	84%	66%
73.8%	82%	83%	70%	68%	70%	70%
87.0%	85%	92%	84%	91%	88%	82%
42.3%	48%	41%	46%	31%	57%	31%
81.8%	89%	87%	85%	85%	66%	79%
90.8%	87%	93%	91%	90%	91%	93%
60.2%	75%	56%	61%	59%	61%	49%
80.5%	78%	91%	73%	89%	74%	78%
56.2%	78%	60%	54%	62%	32%	51%
84.3%	78%	84%	87%	83%	86%	88%
70.8%	66%	70%	45%	76%	87%	81%
76.0%	91%	82%	68%	75%	67%	73%
85.8%	86%	85%	81%	91%	87%	85%
57.2%	57%	62%	53%	57%	54%	60%
88.0%	91%	89%	81%	92%	87%	88%
87.5%	87%	84%	83%	89%	88%	94%
70.2%	68%	77%	61%	76%	65%	74%
76.0%	77%	77%	74%	79%	73%	76%
74.3%	83%	78%	67%	70%	82%	66%
71.3%	76%	71%	67%	74%	64%	76%
80.3%	87%	88%	75%	84%	72%	76%
76.2%	77%	86%	87%	73%	67%	67%
78.8%	84%	79%	68%	80%	82%	80%
80.2%	78%	68%	86%	86%	74%	89%
78.0%	65%	73%	82%	84%	82%	82%
78.8%	86%	81%	74%	76%	80%	76%
67.3%	54%	50%	75%	76%	69%	80%
83.5%	90%	89%	78%	89%	77%	78%
62.5%	68%	72%	41%	70%	67%	57%
74.8%	85%	63%	48%	83%	86%	84%
67.3%	74%	59%	57%	61%	70%	83%
77.8%	84%	80%	79%	85%	61%	78%
71.5%	72%	80%	61%	74%	75%	67%
85.7%	84%	82%	77%	84%	93%	94%
60.7%	61%	74%	47%	63%	54%	65%
72.3%	62%	63%	75%	77%	79%	78%
76.8%	66%	68%	89%	77%	81%	80%
82.3%	89%	84%	72%	85%	81%	83%
74.0%	74%	69%	57%	78%	93%	73%
65.3%	67%	73%	47%	70%	67%	68%
77.3%	76%	84%	61%	85%	88%	70%
83.7%	85%	88%	77%	85%	82%	85%
76.5%	86%	90%	69%	76%	66%	72%
89.3%	81%	88%	83%	96%	90%	98%
76.2%	89%	87%	50%	89%	58%	84%
69.0%	74%	68%	72%	75%	69%	56%
67.7%	75%	71%	59%	71%	74%	56%
89.3%	87%	90%	90%	96%	87%	86%
84.7%	86%	82%	77%	86%	88%	89%
68.3%	72%	77%	52%	64%	82%	63%
79.5%	80%	82%	84%	79%	75%	77%
85.5%	87%	75%	85%	89%	89%	88%
79.0%	67%	63%	92%	91%	75%	86%
76.3%	58%	79%	78%	80%	87%	76%
67.5%	67%	70%	75%	69%	62%	62%
87.2%	90%	85%	86%	86%	88%	88%
83.3%	83%	85%	82%	88%	73%	89%
81.7%	82%	91%	76%	83%	84%	74%
82.7%	86%	88%	91%	80%	78%	73%
79.3%	80%	78%	74%	79%	73%	92%
59.0%	68%	59%	59%	63%	49%	56%
70.3%	75%	71%	59%	74%	67%	76%
83.2%	86%	69%	84%	89%	82%	89%
68.7%	71%	76%	70%	70%	59%	66%
86.2%	81%	80%	84%	86%	92%	94%
86.7%	88%	86%	80%	86%	89%	91%
70.3%	54%	92%	62%	71%	69%	74%
79.8%	80%	82%	70%	83%	79%	85%
53.2%	61%	66%	57%	53%	41%	41%
65.2%	81%	94%	57%	65%	44%	50%
80.5%	87%	87%	68%	78%	90%	73%
65.3%	61%	64%	40%	70%	82%	75%
70.2%	77%	65%	60%	74%	78%	67%
90.5%	90%	90%	87%	93%	90%	93%
69.3%	71%	67%	56%	73%	80%	69%
75.8%	82%	94%	61%	73%	72%	73%
83.0%	79%	84%	78%	83%	80%	94%
82.8%	89%	92%	78%	87%	74%	77%
88.2%	86%	88%	90%	87%	88%	90%
86.7%	91%	94%	93%	86%	77%	79%