	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 66.7%	1st 67.3%	6th 56.3%	3rd 65.1%	5th 61.1%	4th 62.3%
60.2%	71%	64%	64%	64%	41%	57%
70.8%	71%	74%	74%	69%	67%	70%
82.7%	84%	74%	88%	92%	79%	79%
74.5%	86%	77%	63%	72%	69%	80%
45.3%	58%	28%	45%	50%	28%	63%
60.7%	68%	59%	42%	67%	64%	64%
66.0%	71%	66%	53%	67%	74%	65%
54.8%	72%	100%	40%	40%	37%	40%
61.7%	61%	68%	63%	57%	60%	61%
68.5%	65%	79%	48%	68%	84%	67%
86.3%	93%	88%	68%	93%	90%	86%
78.0%	79%	63%	80%	84%	85%	77%
48.7%	72%	70%	10%	72%	21%	47%
60.5%	67%	56%	57%	57%	64%	62%
52.5%	60%	47%	50%	51%	58%	49%
64.8%	67%	67%	71%	66%	57%	61%
76.0%	82%	79%	68%	78%	81%	68%
56.5%	57%	80%	48%	55%	52%	47%
33.8%	34%	39%	24%	49%	23%	34%
64.8%	67%	68%	43%	62%	85%	64%
74.2%	80%	84%	59%	75%	72%	75%
82.5%	87%	84%	68%	88%	86%	82%
56.2%	60%	62%	56%	44%	71%	44%
54.3%	62%	67%	42%	59%	54%	42%
65.8%	69%	71%	58%	65%	69%	63%
66.2%	72%	70%	56%	67%	64%	68%
91.0%	89%	94%	94%	93%	85%	91%
43.0%	54%	50%	29%	38%	52%	35%
71.8%	82%	78%	53%	80%	67%	71%
49.0%	51%	58%	50%	49%	37%	49%
58.7%	68%	56%	50%	68%	44%	66%
60.5%	56%	53%	55%	67%	61%	71%
73.0%	73%	80%	59%	69%	80%	77%
71.7%	75%	76%	57%	72%	74%	76%
39.5%	31%	51%	38%	43%	37%	37%
71.3%	56%	79%	81%	74%	69%	69%
63.3%	65%	71%	46%	64%	67%	67%
51.8%	56%	58%	48%	51%	51%	47%
65.0%	60%	68%	63%	73%	63%	63%
59.2%	56%	63%	59%	55%	70%	52%
58.2%	59%	62%	56%	55%	64%	53%
61.5%	66%	66%	50%	63%	67%	57%
66.2%	60%	75%	63%	75%	62%	62%
73.3%	85%	81%	83%	83%	43%	65%
60.8%	63%	64%	54%	60%	58%	66%
55.7%	54%	53%	52%	61%	51%	63%
43.0%	51%	43%	38%	51%	23%	52%
49.0%	61%	62%	26%	43%	58%	44%
56.8%	65%	70%	48%	52%	51%	55%
61.0%	61%	67%	58%	69%	51%	60%
78.0%	85%	83%	75%	79%	66%	80%
69.8%	71%	73%	69%	70%	69%	67%
79.2%	76%	80%	76%	80%	78%	85%
61.7%	60%	37%	70%	69%	65%	69%