	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 67.9%	2nd 67.8%	5th 63.4%	3rd 66.0%	6th 62.8%	4th 64.7%
43.3%	40%	44%	46%	42%	42%	46%
50.2%	56%	53%	49%	45%	49%	49%
82.3%	80%	83%	77%	88%	83%	83%
86.3%	88%	93%	76%	87%	87%	87%
69.8%	71%	73%	79%	72%	57%	67%
83.2%	91%	88%	89%	89%	61%	81%
66.8%	66%	68%	68%	66%	65%	68%
61.2%	72%	68%	51%	67%	48%	61%
81.2%	72%	87%	91%	74%	91%	72%
62.3%	66%	66%	63%	56%	53%	70%
81.3%	81%	81%	69%	81%	86%	90%
53.0%	60%	52%	48%	51%	61%	46%
63.0%	78%	69%	55%	55%	57%	64%
49.2%	57%	47%	44%	49%	49%	49%
58.2%	66%	60%	64%	40%	77%	42%
57.2%	60%	59%	51%	59%	55%	59%
58.5%	65%	64%	54%	56%	56%	56%
75.8%	80%	80%	73%	73%	76%	73%
66.5%	68%	78%	59%	62%	66%	66%
53.2%	71%	59%	42%	55%	37%	55%
63.5%	63%	66%	63%	63%	63%	63%
71.2%	73%	72%	72%	70%	70%	70%
76.2%	79%	72%	78%	78%	74%	76%
61.0%	59%	62%	67%	59%	52%	67%
43.8%	41%	50%	39%	46%	46%	41%
65.8%	72%	61%	56%	65%	68%	73%
54.5%	57%	57%	61%	44%	51%	57%
63.2%	66%	81%	53%	68%	57%	54%
64.0%	63%	70%	52%	63%	73%	63%
60.3%	67%	64%	52%	67%	61%	51%
55.2%	58%	54%	55%	58%	51%	55%
75.3%	80%	72%	77%	76%	74%	73%
65.7%	69%	65%	64%	68%	60%	68%
52.7%	59%	61%	50%	54%	42%	50%
69.3%	71%	71%	67%	71%	67%	69%
66.2%	64%	68%	64%	64%	68%	69%
57.8%	59%	44%	59%	56%	63%	66%
77.8%	68%	69%	83%	85%	77%	85%
63.5%	65%	70%	58%	64%	58%	66%
82.5%	81%	89%	68%	89%	89%	79%
59.0%	68%	48%	44%	65%	68%	61%
66.4%	72%	50%		67%	72%	71%
65.2%	65%	67%	63%	74%	60%	62%
83.8%	84%	86%	78%	89%	81%	85%
66.5%	74%	72%	77%	71%	43%	62%
40.8%	44%	51%	31%	41%	39%	39%
73.5%	71%	68%	76%	76%	76%	74%
72.7%	70%	66%	74%	74%	77%	75%
56.5%	63%	62%	54%	58%	43%	59%
69.8%	74%	75%	71%	67%	61%	71%
62.0%	69%	74%	49%	67%	54%	59%
61.3%	61%	62%	69%	57%	60%	59%
54.7%	55%	49%	65%	54%	45%	60%
75.5%	74%	78%	74%	75%	78%	74%
74.0%	74%	71%	77%	68%	77%	77%
65.3%	76%	77%	45%	76%	52%	66%
43.7%	54%	37%	49%	49%	35%	38%
56.5%	59%	61%	54%	56%	53%	56%
58.2%	61%	57%	53%	61%	60%	57%
89.7%	98%	95%	82%	82%	91%	90%
69.2%	66%	64%	69%	76%	64%	76%
63.3%	56%	74%	67%	59%	63%	61%
72.3%	69%	71%	74%	73%	72%	75%
74.3%	76%	74%	76%	70%	74%	76%
57.0%	57%	59%		55%	57%	57%
71.3%	71%	73%	70%	68%	73%	73%
65.7%	71%	61%	71%	62%	64%	65%
64.2%	69%	67%	58%	55%	71%	65%
89.2%	92%	83%	90%	90%	90%	90%
57.5%	67%	22%	67%	58%	75%	56%
63.0%	72%	66%	63%	68%	46%	63%
43.8%	59%	41%	38%	47%	34%	44%
34.7%	31%	50%	22%	34%	47%	24%
70.2%	64%	81%	70%	75%	72%	59%
50.0%	61%	52%	50%	52%	39%	46%
67.8%	75%	76%	63%	67%	59%	67%
86.2%	90%	90%	72%	90%	86%	89%
69.2%	56%	74%	71%	70%	73%	71%
57.8%	62%	63%	55%	57%	55%	55%
52.3%	60%	63%	51%	59%	37%	44%
69.3%	65%	100%	63%	100%	44%	44%
88.0%	86%	94%	83%	86%	93%	86%
65.3%	64%	65%	65%	66%	66%	66%
65.7%	69%	74%	63%	68%	52%	68%
53.2%	50%	50%	49%	54%	54%	62%
68.8%	75%	76%	68%	67%	59%	68%
85.3%	92%	90%	85%	83%	76%	86%
78.5%	72%	93%	78%	74%	82%	72%
75.7%	74%	78%	80%	78%	75%	69%
67.7%	71%	76%	70%	66%	60%	63%
70.2%	73%	71%	71%	73%	62%	71%