	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 69.5%	2nd 68.1%	5th 64.3%	3rd 66.4%	6th 62.2%	4th 64.4%
66.5%	64%	68%	65%	69%	62%	71%
76.5%	86%	83%	70%	78%	70%	72%
45.5%	45%	45%	54%	42%	35%	52%
67.8%	72%	66%	66%	77%	58%	68%
56.2%	60%	49%	60%	49%	61%	58%
82.0%	87%	77%	87%	81%	79%	81%
54.2%	52%	66%	56%	57%	52%	42%
86.5%	90%	90%	81%	90%	81%	87%
61.0%	60%	87%	54%	61%	52%	52%
71.2%	77%	71%	71%	71%	59%	78%
48.5%	54%	66%	49%	39%	49%	34%
46.0%	47%	47%	52%	47%	42%	41%
41.3%	46%	75%	31%	34%	28%	34%
60.3%	64%	68%	65%	62%	41%	62%
66.7%	64%	73%	67%	65%	62%	69%
65.8%	66%	74%	62%	64%	54%	75%
66.3%	71%	71%	64%	61%	70%	61%
87.8%	91%	86%	88%	86%	88%	88%
55.0%	62%	56%	48%	58%	56%	50%
59.8%	61%	57%	69%	65%	48%	59%
64.8%	59%	71%	61%	66%	74%	58%
74.3%	76%	67%	80%	73%	77%	73%
87.2%	88%	86%	75%	88%	98%	88%
57.5%	77%	55%	57%	58%	51%	47%
64.2%	61%	66%	66%	64%	64%	64%
52.7%	56%	48%	52%	62%	46%	52%
71.3%	74%	75%	72%	75%	66%	66%
67.8%	63%	59%	82%	62%	91%	50%
74.0%	82%	76%	72%	74%	72%	68%
53.3%	59%	57%	63%	47%	44%	50%
71.0%	77%	73%	66%	78%	66%	66%
83.0%	93%	78%	79%	80%	79%	89%
57.8%	57%	50%	63%	64%	45%	68%
86.0%	85%	94%	86%	86%	86%	79%
75.2%	68%	68%	82%	74%	77%	82%
65.2%	64%	64%	62%	68%	64%	69%
67.7%	73%	68%	60%	68%	68%	69%
69.0%	77%	68%	65%	74%	65%	65%
85.5%	88%	86%	91%	85%	87%	76%
68.3%	69%	67%	69%	68%	68%	69%
57.2%	76%	62%	50%	56%	43%	56%
54.8%	57%	50%	65%	50%	51%	56%
59.2%	71%	79%	49%	44%	69%	43%
58.7%	62%	58%	56%	51%	66%	59%
85.7%	89%	87%	89%	87%	88%	74%
63.8%	65%	66%	63%	64%	61%	64%
73.3%	87%	77%	77%	66%	74%	59%
84.7%	95%	85%	81%	90%	76%	81%
77.2%	88%	63%	70%	88%	78%	76%
63.7%	78%	71%	56%	66%	59%	52%
23.8%	19%	27%	19%	30%	26%	22%
85.7%	88%	87%	81%	81%	88%	89%
65.3%	71%	58%	80%	62%	50%	71%
91.0%	95%	95%	87%	95%	87%	87%
68.2%	70%	71%	69%	66%	62%	71%
64.5%	67%	56%	78%	67%	53%	66%
41.5%	59%	47%	35%	35%	23%	50%
58.7%	56%	64%	58%	58%	58%	58%
67.8%	74%	67%	65%	66%	69%	66%
72.0%	73%	58%	82%	71%	71%	77%
72.7%	74%	74%	71%	72%	74%	71%
41.2%	64%	67%	10%	52%	18%	36%
51.3%	58%	62%	43%	49%	34%	62%
80.0%	83%	90%	78%	78%	77%	74%
54.7%	62%	57%	47%	50%	47%	65%
55.8%	59%	100%	28%	59%	52%	37%
82.3%	74%	80%	89%	86%	72%	93%
80.3%	87%	80%	81%	80%	76%	78%
42.8%	49%	67%	27%	47%	19%	48%
65.2%	77%	62%	52%	66%	68%	66%
88.8%	88%	90%	87%	95%	86%	87%
83.8%	79%	85%	80%	93%	80%	86%
69.8%	74%	74%	67%	65%	65%	74%
65.3%	77%	54%	58%	77%	63%	63%
49.8%	52%	68%	53%	53%	26%	47%
74.5%	72%	74%	70%	74%	79%	78%
40.8%	53%	43%	34%	46%	30%	39%
66.8%	59%	66%	71%	59%	73%	73%
76.8%	83%	73%	69%	80%	80%	76%
61.8%	60%	53%	61%	69%	58%	70%
69.3%	71%	76%	61%	70%	64%	74%
67.5%	75%	81%	50%	75%	66%	58%
37.3%	47%	45%	50%	43%	29%	10%
86.8%	88%	88%	81%	87%	88%	89%
56.5%	66%	58%	59%	58%	40%	58%
68.5%	71%	69%	72%	69%	61%	69%
76.2%	77%	77%	75%	78%	77%	73%
61.8%	64%	61%	56%	61%	64%	65%
84.2%	81%	85%	86%	86%	86%	81%
59.2%	53%	52%	68%	56%	52%	74%
67.3%	78%	50%	63%	78%	77%	58%
38.2%	32%	22%	44%	39%	58%	34%