	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	2nd 67.5%	1st 68.6%	5th 64.7%	3rd 66.5%	6th 62.6%	4th 64.8%
45.8%	42%	67%	42%	42%	40%	42%
47.2%	50%	43%	40%	53%	49%	48%
76.8%	77%	77%	70%	77%	83%	77%
87.7%	89%	100%	75%	85%	87%	90%
70.2%	75%	75%	84%	72%	57%	58%
75.3%	86%	67%	89%	73%	59%	78%
65.5%	68%	63%	68%	63%	68%	63%
59.7%	63%	70%	45%	62%	59%	59%
81.2%	70%	95%	87%	70%	95%	70%
58.5%	66%	67%	55%	59%	51%	53%
78.5%	81%	81%	60%	81%	87%	81%
48.7%	52%	60%	41%	46%	52%	41%
65.5%	72%	76%	61%	64%	59%	61%
49.0%	54%	49%	42%	55%	47%	47%
59.0%	66%	74%	50%	40%	77%	47%
53.7%	60%	59%	41%	59%	48%	55%
55.8%	57%	66%	44%	56%	56%	56%
73.8%	82%	60%	82%	82%	64%	73%
63.0%	65%	67%	62%	62%	60%	62%
64.0%	76%	74%	54%	64%	64%	52%
64.0%	64%	67%	62%	70%	63%	58%
70.2%	73%	72%	66%	70%	70%	70%
72.7%	79%	72%	69%	73%	74%	69%
60.3%	59%	47%	65%	65%	69%	57%
47.8%	35%	57%	50%	50%	45%	50%
66.3%	72%	58%	69%	58%	68%	73%
56.5%	54%	61%	67%	47%	55%	55%
63.0%	66%	77%	51%	68%	49%	67%
67.2%	73%	65%	61%	60%	73%	71%
60.2%	67%	67%	47%	55%	67%	58%
68.7%	71%	70%	64%	73%	68%	66%
74.7%	81%	71%	70%	80%	73%	73%
67.7%	69%	76%	75%	68%	56%	62%
54.2%	55%	61%	57%	55%	42%	55%
71.2%	77%	70%	72%	72%	64%	72%
65.2%	69%	68%	57%	64%	69%	64%
56.3%	54%	41%	55%	60%	62%	66%
79.2%	83%	67%	85%	87%	73%	80%
64.7%	65%	60%	70%	69%	62%	62%
74.8%	75%	86%	66%	79%	72%	71%
58.3%	62%	53%	37%	57%	75%	66%
68.7%	82%	30%	66%	79%	80%	75%
61.3%	55%	58%	70%	66%	53%	66%
80.3%	85%	73%	72%	85%	89%	78%
67.8%	69%	77%	75%	77%	43%	66%
42.7%	45%	59%	25%	51%	31%	45%
76.3%	73%	66%	82%	76%	79%	82%
70.5%	67%	67%	76%	72%	69%	72%
57.5%	59%	58%	62%	62%	45%	59%
70.0%	71%	70%	75%	70%	64%	70%
66.7%	76%	74%	55%	70%	65%	60%
61.0%	62%	62%	66%	54%	60%	62%
57.8%	56%	49%	73%	56%	48%	65%
78.2%	76%	82%	82%	80%	71%	78%
74.7%	76%	67%	83%	71%	75%	76%
65.2%	68%	77%	45%	82%	43%	76%
51.8%	74%	53%	53%	54%	39%	38%
56.2%	61%	61%	53%	56%	53%	53%
52.0%	49%	55%	49%	55%	49%	55%
78.8%	71%	90%	91%	65%	74%	82%
69.2%	68%	67%	77%	65%	62%	76%
61.5%	61%	64%	66%	60%	58%	60%
69.7%	66%	70%	72%	72%	66%	72%
71.8%	74%	70%	69%	76%	69%	73%
57.8%	60%	58%	58%	56%	59%	56%
73.2%	74%	67%	76%	73%	80%	69%
65.5%	71%	71%	67%	60%	62%	62%
60.8%	67%	67%	52%	60%	58%	61%
85.2%	81%	90%	91%	83%	72%	94%
70.0%	52%	77%	77%	74%	80%	60%
63.7%	72%	67%	70%	67%	49%	57%
74.0%	70%	74%	70%	74%	88%	68%
27.5%	24%	32%	28%	31%	23%	27%
70.5%	67%	84%	69%	67%	64%	72%
69.5%	71%	65%	65%	80%	80%	56%
67.2%	65%	77%	77%	65%	54%	65%
89.0%	89%	89%	89%	89%	89%	89%
72.5%	65%	74%	72%	78%	68%	78%
58.7%	56%	63%	63%	63%	44%	63%
51.3%	60%	77%	55%	59%	13%	44%
59.2%	72%	100%	51%	51%	37%	44%
92.2%	87%	94%	100%	91%	91%	90%
64.8%	69%	65%	57%	66%	66%	66%
66.3%	62%	75%	66%	71%	53%	71%
54.5%	55%	58%	55%	52%	55%	52%
67.0%	68%	66%	76%	66%	60%	66%
82.2%	93%	86%	74%	83%	76%	81%
82.3%	81%	86%	82%	82%	81%	82%
76.3%	76%	80%	69%	80%	72%	81%
65.0%	63%	76%	59%	66%	63%	63%
68.0%	72%	71%	77%	68%	60%	60%