	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	1st 77.9%	3rd 76.5%	5th 72.5%	2nd 77.5%	6th 72.4%	4th 73.4%
74.5%	57%	71%	82%	83%	87%	67%
79.3%	75%	77%	80%	85%	85%	74%
74.7%	71%	76%	82%	74%	64%	81%
76.3%	83%	78%	70%	84%	69%	74%
84.7%	87%	84%	83%	83%	84%	87%
85.3%	87%	80%	92%	88%	75%	90%
67.5%	54%	87%	65%	63%	63%	73%
87.7%	91%	84%	82%	81%	96%	92%
84.8%	76%	92%	80%	85%	91%	85%
81.7%	75%	79%	84%	88%	84%	80%
43.2%	52%	52%	36%	44%	35%	40%
77.5%	83%	87%	84%	84%	59%	68%
56.8%	47%	90%	36%	61%	47%	60%
75.7%	82%	93%	76%	79%	61%	63%
77.8%	82%	60%	82%	79%	79%	85%
91.0%	91%	91%	91%	91%	91%	91%
85.2%	93%	87%	80%	73%	86%	92%
80.8%	92%	80%	75%	89%	74%	75%
65.3%	66%	80%	36%	62%	77%	71%
66.5%	69%	65%	74%	68%	67%	56%
69.5%	67%	72%	63%	74%	72%	69%
85.5%	79%	89%	90%	86%	83%	86%
86.5%	94%	96%	74%	97%	91%	67%
51.5%	0%	34%	72%	84%	64%	55%
78.2%	77%	59%	87%	83%	85%	78%
72.8%	76%	73%	66%	70%	75%	77%
75.0%	75%	44%	84%	85%	82%	80%
76.0%	73%	84%	82%	73%	71%	73%
72.8%	79%	48%	71%	77%	85%	77%
75.2%	78%	82%	84%	79%	58%	70%
73.7%	82%	54%	70%	80%	71%	85%
80.7%	91%	84%	76%	87%	72%	74%
82.8%	87%	90%	79%	81%	75%	85%
91.2%	84%	87%	93%	96%	95%	92%
82.3%	82%	67%	88%	88%	83%	86%
82.5%	89%	84%	75%	86%	85%	76%
75.5%	80%	74%	73%	79%	71%	76%
68.8%	78%	66%	64%	73%	66%	66%
78.0%	76%	77%	76%	81%	80%	78%
74.3%	77%	46%	85%	78%	80%	80%
77.5%	88%	87%	75%	77%	74%	64%
85.3%	92%	90%	80%	89%	82%	79%
61.7%	68%	94%	57%	61%	35%	55%
65.2%	73%	70%	59%	68%	63%	58%
83.0%	82%	58%	94%	92%	90%	82%
80.0%	82%	75%	82%	87%	78%	76%
74.3%	83%	72%	65%	80%	67%	79%
86.3%	98%	86%	80%	94%	74%	86%
71.2%	74%	75%	74%	71%	65%	68%
81.0%	84%	77%	80%	86%	79%	80%
47.0%	36%	88%	37%	33%	41%	47%
82.3%	81%	87%	89%	77%	73%	87%
76.2%	78%	80%	87%	80%	52%	80%
98.0%	98%	98%	98%	98%	98%	98%
76.3%	82%	83%	68%	72%	69%	84%
73.2%	80%	79%	85%	71%	52%	72%
65.5%	82%	70%	63%	65%	66%	47%
81.8%	94%	94%	76%	78%	73%	76%
87.5%	97%	65%	88%	91%	90%	94%
73.3%	75%	75%	71%	74%	70%	75%
74.0%	68%	68%	84%	73%	73%	78%
50.7%	66%	78%	41%	58%	24%	37%
74.3%	82%	85%	75%	73%	62%	69%
76.0%	85%	77%	74%	82%	74%	64%
77.8%	87%	95%	81%	69%	67%	68%
54.0%	65%	92%	20%	46%	35%	66%
79.5%	72%	54%	88%	91%	90%	82%
75.3%	75%	41%	84%	89%	80%	83%
59.0%	65%	91%	28%	64%	41%	65%
73.2%	84%	90%	59%	77%	70%	59%
80.0%	86%	83%	76%	84%	68%	83%
75.2%	77%	57%	81%	80%	78%	78%
69.5%	74%	65%	56%	75%	82%	65%
77.7%	91%	77%	59%	88%	68%	83%
63.3%	65%	80%	60%	62%	60%	53%
82.7%	89%	87%	80%	83%	79%	78%
74.7%	93%	82%	65%	74%	72%	62%
77.7%	74%	88%	76%	72%	72%	84%
81.3%	86%	81%	70%	78%	85%	88%
72.7%	79%	73%	65%	72%	72%	75%
77.0%	81%	81%	76%	79%	75%	70%
63.7%	62%	81%	55%	60%	71%	53%
56.2%	79%	79%	10%	85%	74%	10%
83.2%	78%	84%	87%	87%	77%	86%
66.0%	84%	60%	72%	60%	69%	51%
73.2%	79%	70%	62%	79%	81%	68%
82.3%	93%	84%	75%	86%	83%	73%
82.8%	92%	93%	72%	84%	70%	86%
87.5%	90%	70%	92%	92%	89%	92%
72.5%	73%	72%	79%	70%	69%	72%
81.5%	89%	68%	83%	81%	87%	81%
52.0%	41%	49%	52%	48%	56%	66%