	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 73.8%	1st 74.6%	6th 66.9%	3rd 73.6%	4th 72.1%	5th 70.3%
63.5%	78%	59%	67%	61%	63%	53%
90.3%	90%	89%	97%	94%	81%	91%
90.5%	94%	94%	90%	97%	77%	91%
73.7%	81%	77%	65%	72%	70%	77%
65.5%	73%	47%	59%	60%	71%	83%
58.7%	51%	62%	44%	64%	75%	56%
67.2%	71%	71%	48%	70%	76%	67%
58.3%	75%	100%	39%	37%	55%	44%
74.7%	73%	70%	68%	84%	75%	78%
66.5%	66%	73%	54%	69%	69%	68%
72.3%	65%	77%	64%	71%	83%	74%
84.3%	82%	75%	93%	88%	81%	87%
54.5%	61%	75%	53%	53%	41%	44%
81.3%	87%	84%	78%	84%	75%	80%
86.7%	91%	90%	79%	89%	82%	89%
85.5%	88%	88%	84%	87%	81%	85%
66.3%	71%	74%	55%	72%	67%	59%
81.5%	87%	93%	75%	82%	73%	79%
51.8%	58%	50%	53%	54%	48%	48%
77.0%	82%	81%	64%	81%	83%	71%
80.8%	86%	80%	67%	85%	82%	85%
79.7%	82%	86%	62%	85%	87%	76%
47.0%	52%	47%	54%	35%	53%	41%
82.3%	88%	81%	83%	81%	80%	81%
81.3%	88%	83%	75%	85%	74%	83%
86.7%	90%	90%	80%	96%	72%	92%
91.2%	85%	92%	95%	93%	89%	93%
75.3%	84%	85%	61%	76%	81%	65%
70.5%	74%	76%	60%	76%	73%	64%
60.8%	66%	60%	64%	63%	52%	60%
58.5%	65%	63%	47%	60%	66%	50%
55.7%	50%	43%	41%	60%	72%	68%
64.8%	59%	66%	50%	69%	76%	69%
79.5%	82%	85%	72%	85%	74%	79%
39.5%	38%	41%	46%	33%	41%	38%
82.0%	65%	91%	89%	82%	86%	79%
66.2%	71%	72%	53%	69%	72%	60%
53.5%	52%	43%	57%	47%	68%	54%
80.2%	73%	83%	77%	84%	84%	80%
78.0%	66%	87%	74%	84%	88%	69%
76.7%	69%	84%	76%	78%	84%	69%
62.0%	69%	68%	44%	61%	75%	55%
67.0%	62%	80%	60%	71%	68%	61%
76.2%	77%	68%	87%	88%	70%	67%
71.8%	72%	73%	61%	79%	75%	71%
68.0%	69%	67%	71%	70%	59%	72%
49.8%	63%	53%	53%	46%	35%	49%
52.7%	58%	60%	37%	54%	63%	44%
82.5%	97%	87%	76%	80%	82%	73%
72.8%	75%	79%	77%	72%	62%	72%
81.0%	82%	86%	83%	85%	68%	82%
86.0%	85%	81%	82%	91%	91%	86%
88.0%	83%	84%	83%	89%	93%	96%
83.5%	85%	76%	86%	91%	74%	89%