	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 73.7%	2nd 72.3%	6th 68.5%	3rd 71.2%	5th 69.4%	4th 70.7%
42.8%	39%	64%	43%	31%	36%	44%
72.3%	75%	79%	70%	72%	70%	68%
74.7%	78%	68%	72%	72%	81%	77%
66.5%	65%	72%	59%	69%	64%	70%
82.7%	85%	88%	78%	82%	90%	73%
72.7%	79%	68%	81%	77%	66%	65%
88.3%	90%	82%	92%	82%	92%	92%
74.3%	90%	66%	62%	83%	71%	74%
44.0%	38%	47%	52%	41%	51%	35%
83.2%	90%	89%	81%	84%	77%	78%
60.2%	58%	64%	52%	62%	67%	58%
69.0%	77%	72%	67%	59%	74%	65%
81.5%	81%	84%	84%	82%	79%	79%
77.7%	86%	82%	82%	75%	63%	78%
61.2%	72%	67%	56%	54%	71%	47%
85.2%	93%	87%	70%	93%	84%	84%
75.3%	72%	79%	68%	74%	78%	81%
66.7%	79%	48%	83%	61%	69%	60%
79.5%	85%	69%	83%	87%	78%	75%
57.8%	72%	68%	48%	50%	68%	41%
76.0%	70%	81%	81%	70%	75%	79%
80.2%	88%	81%	59%	88%	81%	84%
55.5%	69%	65%	53%	60%	33%	53%
81.8%	80%	48%	87%	93%	93%	90%
49.8%	29%	57%	59%	43%	62%	49%
80.2%	86%	67%	85%	73%	88%	82%
67.8%	63%	72%	79%	58%	61%	74%
72.2%	75%	77%	77%	72%	64%	68%
67.2%	72%	82%	62%	62%	57%	68%
70.7%	83%	69%	52%	71%	74%	75%
80.5%	77%	81%	79%	80%	83%	83%
60.2%	58%	39%	67%	60%	70%	67%
76.7%	78%	67%	74%	77%	83%	81%
58.3%	66%	59%	49%	58%	67%	51%
79.0%	80%	69%	79%	85%	80%	81%
51.2%	60%	61%	42%	48%	39%	57%
63.2%	59%	49%	68%	67%	69%	67%
69.5%	72%	54%	76%	71%	66%	78%
72.7%	68%	65%	72%	74%	79%	78%
52.8%	61%	63%	39%	49%	55%	50%
52.5%	61%	67%	25%	53%	52%	57%
53.2%	72%	35%	54%	50%	60%	48%
72.5%	68%	81%	78%	68%	76%	64%
72.2%	69%	71%	70%	79%	67%	77%
75.3%	82%	75%	75%	80%	61%	79%
65.8%	67%	90%	51%	67%	56%	64%
72.8%	81%	69%	73%	69%	68%	77%
73.3%	58%	60%	83%	82%	75%	82%
74.7%	79%	84%	65%	77%	68%	75%
75.0%	78%	80%	62%	79%	76%	75%
65.0%	70%	61%	62%	69%	62%	66%
71.2%	78%	69%	60%	80%	72%	68%
69.8%	68%	75%	69%	70%	68%	69%
78.3%	87%	83%	76%	77%	76%	71%
74.8%	77%	82%	87%	66%	56%	81%
69.2%	72%	81%	46%	92%	49%	75%
66.3%	87%	57%	68%	70%	62%	54%
79.2%	88%	86%	70%	89%	70%	72%
76.3%	91%	86%	76%	82%	54%	69%
83.5%	90%	79%	64%	87%	93%	88%
63.5%	72%	64%	57%	55%	68%	65%
64.5%	59%	76%	66%	61%	56%	69%
68.8%	56%	83%	73%	59%	69%	73%
54.5%	62%	49%	55%	55%	47%	59%
81.3%	96%	94%	70%	87%	70%	71%
64.7%	70%	62%	68%	61%	67%	60%
75.2%	69%	92%	82%	69%	71%	68%
69.8%	71%	64%	64%	71%	76%	73%
66.7%	65%	64%	71%	72%	68%	60%
65.2%	76%	38%	74%	75%	54%	74%
84.2%	91%	89%	87%	87%	69%	82%
75.8%	75%	82%	74%	74%	82%	68%
50.2%	41%	80%	41%	49%	39%	51%
88.8%	97%	85%	93%	84%	90%	84%
81.7%	75%	83%	83%	83%	83%	83%
89.7%	90%	92%	86%	96%	90%	84%
94.0%	94%	94%	94%	94%	94%	94%
61.8%	35%	83%	69%	48%	67%	69%
84.5%	88%	87%	76%	82%	86%	88%
69.5%	74%	94%	63%	78%	50%	58%
69.2%	75%	83%	77%	65%	49%	66%
68.3%	68%	65%	74%	71%	64%	68%
72.2%	78%	73%	55%	78%	73%	76%
69.0%	72%	66%	63%	70%	75%	68%
81.3%	84%	73%	76%	81%	88%	86%
68.2%	73%	73%	54%	69%	68%	72%
70.0%	75%	80%	67%	63%	64%	71%
68.2%	58%	69%	73%	60%	73%	76%
86.3%	91%	73%	77%	91%	93%	93%
77.3%	76%	74%	68%	80%	87%	79%
71.8%	76%	71%	66%	79%	60%	79%