	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 68.5%	1st 69.7%	6th 61.7%	3rd 68.1%	5th 62.7%	4th 67.2%
73.7%	70%	71%	63%	83%	77%	78%
71.0%	63%	71%	74%	72%	73%	73%
70.5%	67%	68%	70%	76%	72%	70%
58.8%	54%	66%	54%	64%	47%	68%
93.3%	95%	88%	94%	95%	94%	94%
58.2%	65%	74%	47%	56%	51%	56%
77.2%	69%	87%	87%	74%	76%	70%
52.5%	51%	63%	34%	52%	55%	60%
80.5%	80%	89%	76%	76%	85%	77%
58.8%	62%	65%	59%	59%	45%	63%
86.3%	90%	89%	89%	86%	78%	86%
40.0%	45%	49%	31%	43%	26%	46%
81.5%	82%	81%	78%	83%	82%	83%
73.0%	78%	65%	73%	78%	64%	80%
67.3%	75%	63%	60%	65%	68%	73%
64.8%	67%	67%	54%	72%	65%	64%
56.3%	71%	69%	45%	60%	40%	53%
55.8%	64%	64%	35%	63%	60%	49%
60.3%	63%	64%	53%	53%	66%	63%
77.5%	63%	79%	85%	79%	83%	76%
73.5%	84%	75%	58%	75%	76%	73%
66.5%	77%	73%	51%	66%	63%	69%
64.2%	69%	74%	71%	73%	30%	68%
73.5%	82%	81%	67%	71%	65%	75%
70.2%	71%	68%	75%	69%	70%	68%
71.2%	62%	75%	67%	79%	63%	81%
52.8%	56%	62%	38%	54%	56%	51%
51.3%	61%	59%	38%	50%	58%	42%
43.8%	45%	47%	39%	57%	20%	55%
59.0%	58%	70%	55%	68%	53%	50%
56.0%	61%	55%	49%	52%	63%	56%
62.0%	64%	59%	64%	59%	62%	64%
53.7%	53%	50%	53%	58%	55%	53%
66.3%	56%	80%	73%	58%	73%	58%
60.5%	73%	41%	61%	71%	45%	72%
63.8%	72%	68%	57%	65%	62%	59%
67.8%	75%	60%	53%	72%	75%	72%
85.0%	90%	89%	93%	88%	71%	79%
41.8%	47%	54%	30%	35%	40%	45%
97.5%	98%	97%	98%	97%	100%	95%
64.5%	68%	74%	60%	64%	62%	59%
80.3%	78%	83%	76%	79%	78%	88%
69.2%	73%	73%	66%	78%	51%	74%