	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 71.7%	2nd 70.5%	6th 66.1%	3rd 69.7%	5th 68.7%	4th 69.0%
33.3%	24%	74%	19%	21%	31%	31%
72.2%	79%	76%	61%	76%	66%	75%
64.2%	64%	74%	68%	56%	65%	58%
78.0%	93%	67%	71%	75%	74%	88%
73.2%	84%	80%	84%	89%	40%	62%
70.7%	77%	82%	76%	71%	55%	63%
78.5%	77%	72%	80%	84%	87%	71%
85.5%	90%	86%	74%	88%	87%	88%
60.8%	61%	84%	10%	60%	89%	61%
89.5%	90%	95%	94%	84%	90%	84%
72.8%	67%	76%	65%	84%	67%	78%
83.3%	87%	85%	83%	74%	92%	79%
75.8%	71%	71%	80%	87%	66%	80%
68.8%	66%	70%	76%	75%	62%	64%
61.5%	75%	66%	63%	42%	74%	49%
86.0%	98%	85%	57%	96%	91%	89%
64.0%	62%	42%	74%	72%	72%	62%
60.0%	74%	51%	76%	66%	34%	59%
60.7%	61%	67%	59%	62%	53%	62%
75.7%	91%	83%	68%	70%	77%	65%
64.8%	59%	69%	84%	65%	36%	76%
56.5%	65%	57%	43%	51%	65%	58%
58.8%	61%	65%	47%	48%	70%	62%
79.3%	79%	78%	72%	83%	79%	85%
33.0%	23%	43%	32%	25%	42%	33%
69.5%	79%	55%	73%	56%	77%	77%
74.2%	80%	79%	67%	72%	69%	78%
66.8%	79%	76%	49%	64%	64%	69%
72.5%	73%	72%	76%	64%	77%	73%
56.0%	68%	68%	28%	59%	68%	45%
79.2%	74%	86%	66%	86%	86%	77%
58.8%	69%	65%	47%	61%	58%	53%
70.7%	77%	74%	70%	67%	68%	68%
70.7%	77%	68%	65%	75%	70%	69%
61.0%	61%	63%	57%	55%	66%	64%
73.5%	71%	73%	71%	77%	77%	72%
80.0%	85%	75%	84%	75%	81%	80%
69.8%	77%	55%	78%	72%	73%	64%
74.3%	75%	72%	78%	72%	65%	84%
64.2%	65%	73%	50%	63%	71%	63%
59.7%	62%	49%	38%	48%	91%	70%
65.7%	63%	35%	80%	82%	58%	76%
62.2%	54%	62%	65%	69%	56%	67%
71.8%	74%	72%	66%	69%	73%	77%
77.8%	86%	80%	66%	82%	72%	81%
65.3%	68%	61%	49%	90%	56%	68%
76.2%	77%	64%	82%	82%	84%	68%
59.3%	65%	58%	57%	57%	60%	59%
65.5%	67%	69%	64%	60%	72%	61%
77.2%	80%	81%	76%	80%	72%	74%
86.8%	92%	78%	86%	91%	87%	87%
39.8%	33%	46%	42%	35%	47%	36%
77.2%	78%	76%	72%	85%	80%	72%
74.8%	84%	84%	68%	72%	70%	71%
77.2%	83%	80%	79%	77%	64%	80%
73.2%	87%	54%	67%	79%	64%	88%
65.8%	84%	72%	62%	72%	48%	57%
56.7%	75%	62%	53%	57%	34%	59%
80.5%	80%	81%	90%	86%	76%	70%
61.5%	54%	61%	69%	46%	79%	60%
69.5%	76%	71%	57%	66%	74%	73%
80.7%	79%	80%	74%	85%	82%	84%
82.7%	78%	80%	86%	71%	86%	95%
59.3%	65%	27%	68%	69%	65%	62%
70.8%	66%	71%	82%	73%	71%	62%
76.3%	81%	44%	87%	93%	75%	78%
77.3%	81%	86%	81%	68%	76%	72%
62.0%	55%	73%	52%	50%	73%	69%
84.5%	96%	82%	80%	94%	83%	72%
53.8%	0%	71%	59%	69%	54%	70%
67.3%	67%	72%	58%	61%	77%	69%
81.8%	79%	80%	83%	86%	80%	83%
40.8%	41%	59%	34%	47%	25%	39%
80.3%	76%	91%	71%	78%	78%	88%
79.8%	91%	76%	76%	83%	86%	67%
77.5%	81%	75%	80%	84%	73%	72%
85.0%	85%	85%	85%	85%	85%	85%
48.3%	46%	58%	50%	41%	44%	51%
59.0%	61%	63%	51%	61%	62%	56%
51.3%	65%	72%	48%	64%	19%	40%
58.0%	72%	82%	47%	55%	56%	36%
77.0%	75%	78%	73%	74%	81%	81%
64.7%	70%	64%	51%	64%	73%	66%
49.3%	51%	40%	53%	48%	57%	47%
84.3%	83%	92%	83%	82%	79%	87%
64.8%	70%	70%	60%	61%	67%	61%
87.0%	91%	76%	93%	84%	87%	91%
69.5%	63%	83%	71%	57%	71%	72%
79.8%	82%	86%	82%	84%	72%	73%
90.0%	84%	96%	75%	96%	91%	98%
70.5%	77%	59%	58%	73%	71%	85%