	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 67.5%	1st 68.0%	5th 65.8%	3rd 67.3%	6th 62.7%	4th 67.0%
75.7%	75%	77%	78%	79%	68%	77%
65.5%	66%	69%	59%	68%	66%	65%
69.5%	85%	72%	71%	71%	58%	60%
91.5%	88%	90%	83%	92%	98%	98%
71.7%	82%	69%	78%	74%	54%	73%
65.2%	56%	72%	62%	67%	67%	67%
78.8%	85%	91%	72%	73%	74%	78%
50.2%	48%	79%	23%	47%	64%	40%
68.5%	70%	70%	69%	69%	62%	71%
81.3%	73%	81%	84%	84%	96%	70%
64.0%	75%	85%	60%	60%	44%	60%
42.8%	38%	33%	60%	48%	33%	45%
89.7%	97%	100%	90%	81%	79%	91%
91.5%	88%	90%	83%	92%	98%	98%
63.8%	72%	59%	57%	63%	63%	69%
46.5%	52%	47%	40%	42%	44%	54%
71.5%	74%	69%	76%	73%	61%	76%
81.7%	80%	78%	80%	82%	85%	85%
67.0%	65%	68%	63%	68%	66%	72%
45.5%	51%	53%	50%	52%	27%	40%
67.7%	72%	71%	62%	68%	63%	70%
67.5%	71%	49%	61%	81%	59%	84%
97.3%	96%	99%	100%	92%	99%	98%
44.5%	46%	47%	44%	40%	39%	51%
89.7%	97%	100%	90%	81%	79%	91%
51.3%	50%	46%	65%	47%	46%	54%
35.5%	37%	23%	37%	37%	40%	39%
66.8%	65%	57%	77%	75%	56%	71%
87.8%	87%	90%	71%	85%	98%	96%
58.3%	53%	57%	57%	65%	60%	58%
69.7%	70%	69%	70%	76%	57%	76%
70.2%	70%	70%	75%	66%	70%	70%
72.7%	68%	68%	79%	79%	73%	69%
59.0%	59%	62%	60%	60%	59%	54%
48.2%	46%	49%	48%	47%	49%	50%
68.5%	69%	71%	73%	61%	68%	69%
50.8%	47%	51%	55%	53%	48%	51%
40.8%	41%	49%	38%	44%	38%	35%
48.3%	51%	51%	54%	58%	29%	47%
79.3%	74%	88%	74%	78%	84%	78%
61.2%	67%	69%	65%	62%	42%	62%
62.8%	63%	68%	62%	60%	60%	64%
80.7%	79%	85%	68%	90%	84%	78%
61.8%	59%	61%	71%	64%	55%	61%
62.7%	67%	61%	67%	73%	48%	60%
68.0%	81%	66%	66%	67%	73%	55%