	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 69.9%	1st 70.0%	5th 60.7%	3rd 68.8%	6th 59.6%	4th 67.8%
42.7%	39%	37%	49%	43%	34%	54%
63.3%	67%	70%	49%	61%	68%	65%
47.3%	59%	57%	32%	54%	41%	41%
66.5%	68%	73%	62%	73%	54%	69%
73.7%	82%	75%	62%	73%	75%	75%
76.8%	72%	79%	73%	77%	83%	77%
71.5%	76%	65%	73%	78%	62%	75%
75.7%	79%	77%	68%	79%	79%	72%
67.0%	67%	83%	57%	65%	63%	67%
82.2%	93%	89%	78%	87%	64%	82%
71.2%	82%	87%	76%	74%	38%	70%
57.0%	61%	51%	70%	62%	40%	58%
68.3%	84%	85%	65%	83%	26%	67%
69.8%	68%	71%	62%	72%	69%	77%
60.0%	66%	54%	55%	65%	60%	60%
46.8%	49%	58%	44%	51%	34%	45%
47.5%	51%	47%	40%	54%	50%	43%
70.8%	73%	68%	58%	78%	74%	74%
51.7%	56%	53%	38%	55%	55%	53%
66.0%	63%	78%	78%	73%	43%	61%
72.8%	72%	80%	64%	77%	65%	79%
63.8%	75%	61%	61%	70%	41%	75%
93.7%	96%	93%	94%	83%	97%	99%
68.0%	69%	72%	63%	66%	66%	72%
69.0%	83%	84%	68%	84%	27%	68%
62.0%	59%	68%	78%	62%	44%	61%
75.7%	78%	75%	80%	76%	72%	73%
69.0%	73%	67%	77%	70%	56%	71%
79.3%	87%	98%	10%	85%	98%	98%
49.2%	47%	59%	31%	47%	64%	47%
44.5%	43%	51%	49%	43%	31%	50%
58.8%	59%	62%	59%	59%	55%	59%
79.8%	80%	79%	80%	83%	74%	83%
65.2%	65%	69%	71%	65%	66%	55%
75.7%	83%	74%	71%	82%	73%	71%
84.5%	90%	87%	71%	80%	92%	87%
82.0%	84%	84%	84%	76%	83%	81%
50.0%	51%	45%	51%	47%	54%	52%
55.5%	56%	62%	60%	60%	35%	60%
68.3%	70%	74%	67%	76%	51%	72%
60.5%	64%	55%	57%	58%	62%	67%
66.0%	70%	69%	60%	65%	68%	64%
52.2%	55%	54%	41%	55%	56%	52%
75.2%	92%	87%	10%	91%	80%	91%
78.8%	85%	82%	82%	74%	67%	83%
66.7%	74%	72%	66%	72%	54%	62%