	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	4th 63.1%	1st 67.0%	6th 52.7%	3rd 63.3%	2nd 63.9%	5th 61.3%
64.5%	78%	67%	64%	63%	63%	52%
87.0%	88%	86%	86%	91%	93%	78%
78.3%	83%	79%	79%	85%	76%	68%
74.8%	76%	79%	75%	81%	69%	69%
28.2%	28%	15%	18%	29%	33%	46%
57.8%	50%	62%	38%	67%	68%	62%
70.7%	73%	78%	49%	70%	74%	80%
58.3%	74%	100%	34%	44%	54%	44%
63.8%	70%	62%	52%	74%	66%	59%
48.5%	47%	54%	28%	48%	64%	50%
64.3%	68%	73%	44%	56%	73%	72%
78.8%	75%	83%	82%	79%	75%	79%
44.8%	61%	63%	10%	53%	41%	41%
84.5%	83%	89%	91%	83%	79%	82%
80.7%	87%	84%	72%	80%	81%	80%
78.5%	75%	81%	78%	77%	87%	73%
71.2%	72%	75%	70%	71%	76%	63%
63.7%	63%	83%	51%	63%	62%	60%
26.5%	26%	34%	15%	36%	21%	27%
67.3%	69%	75%	49%	66%	79%	66%
72.5%	70%	72%	56%	78%	81%	78%
69.7%	79%	73%	46%	67%	86%	67%
38.8%	44%	34%	42%	32%	48%	33%
71.3%	73%	86%	57%	81%	67%	64%
87.5%	86%	91%	80%	89%	90%	89%
81.5%	83%	87%	69%	78%	87%	85%
83.3%	86%	84%	73%	85%	88%	84%
63.2%	64%	82%	49%	61%	66%	57%
74.5%	82%	89%	55%	82%	69%	70%
32.3%	29%	42%	28%	32%	24%	39%
51.2%	49%	36%	52%	58%	52%	60%
31.8%	22%	27%	19%	39%	41%	43%
48.7%	48%	55%	27%	50%	66%	46%
68.8%	68%	73%	59%	69%	72%	72%
21.8%	14%	30%	23%	24%	20%	20%
84.0%	78%	90%	81%	89%	92%	74%
59.5%	66%	72%	39%	58%	61%	61%
26.0%	27%	27%	23%	26%	27%	26%
84.3%	86%	80%	84%	84%	89%	83%
61.7%	58%	70%	56%	63%	71%	52%
78.8%	76%	93%	71%	84%	81%	68%
51.5%	59%	59%	35%	49%	59%	48%
43.8%	38%	40%	42%	53%	45%	45%
76.2%	72%	80%	82%	70%	73%	80%
62.8%	61%	60%	52%	66%	71%	67%
37.8%	34%	38%	36%	38%	32%	49%
27.0%	31%	29%	20%	33%	16%	33%
47.5%	52%	49%	31%	54%	54%	45%
56.8%	64%	73%	45%	57%	51%	51%
64.0%	65%	73%	59%	66%	48%	73%
76.0%	78%	87%	62%	68%	81%	80%
80.2%	82%	73%	84%	82%	82%	78%
82.2%	88%	91%	75%	81%	73%	85%
51.8%	51%	49%	48%	55%	52%	56%