	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 63.7%	1st 65.5%	6th 53.0%	4th 62.9%	3rd 63.2%	5th 61.2%
63.5%	78%	62%	64%	62%	63%	52%
87.2%	88%	87%	86%	93%	91%	78%
78.2%	83%	78%	79%	85%	76%	68%
74.8%	76%	79%	68%	84%	69%	73%
29.5%	28%	22%	22%	29%	33%	43%
57.8%	54%	62%	42%	67%	69%	53%
71.5%	73%	88%	49%	67%	74%	78%
41.3%	73%	7%	34%	37%	56%	41%
62.0%	69%	61%	52%	65%	66%	59%
49.7%	52%	56%	28%	50%	66%	46%
65.3%	68%	75%	43%	63%	71%	72%
79.3%	78%	83%	82%	79%	75%	79%
44.7%	61%	66%	10%	53%	37%	41%
83.8%	83%	83%	90%	82%	83%	82%
80.0%	86%	83%	72%	82%	77%	80%
78.2%	74%	81%	78%	76%	87%	73%
73.0%	72%	74%	70%	72%	81%	69%
63.5%	61%	84%	53%	61%	62%	60%
25.7%	26%	36%	15%	29%	21%	27%
66.5%	69%	74%	49%	66%	76%	65%
75.3%	75%	81%	59%	78%	81%	78%
69.3%	79%	71%	46%	67%	86%	67%
39.2%	44%	42%	41%	32%	44%	32%
71.7%	77%	88%	52%	84%	67%	62%
85.7%	86%	82%	80%	87%	90%	89%
82.7%	85%	88%	69%	78%	91%	85%
85.2%	86%	84%	84%	82%	89%	86%
59.7%	64%	68%	49%	61%	66%	50%
74.0%	81%	87%	59%	82%	69%	66%
31.2%	29%	35%	28%	32%	24%	39%
52.5%	49%	36%	52%	61%	53%	64%
30.2%	22%	30%	18%	39%	29%	43%
48.7%	48%	55%	27%	46%	66%	50%
68.3%	68%	73%	59%	73%	68%	69%
21.5%	14%	28%	23%	24%	20%	20%
83.3%	79%	90%	81%	84%	92%	74%
59.5%	64%	72%	40%	61%	59%	61%
27.8%	27%	33%	23%	27%	25%	32%
83.8%	90%	78%	84%	82%	86%	83%
62.3%	58%	71%	56%	63%	71%	55%
76.8%	76%	91%	71%	72%	81%	70%
50.7%	59%	60%	35%	43%	59%	48%
42.5%	38%	40%	42%	45%	45%	45%
80.0%	83%	81%	82%	77%	73%	84%
61.3%	61%	61%	52%	61%	66%	67%
40.3%	34%	48%	36%	38%	32%	54%
28.2%	28%	29%	20%	38%	21%	33%
47.5%	53%	48%	31%	58%	50%	45%
56.7%	64%	71%	45%	58%	51%	51%
62.3%	64%	72%	59%	66%	40%	73%
77.0%	81%	89%	62%	69%	81%	80%
80.7%	82%	75%	89%	81%	79%	78%
81.3%	88%	89%	75%	87%	73%	76%
52.7%	51%	49%	48%	61%	52%	55%