	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 68.3%	4th 66.2%	3rd 67.3%	1st 68.8%	6th 64.6%	5th 66.0%
73.2%	68%	68%	85%	73%	67%	78%
78.0%	85%	33%	91%	85%	85%	89%
75.8%	75%	71%	75%	84%	75%	75%
67.3%	53%	75%	64%	78%	64%	70%
85.0%	84%	82%	76%	100%	84%	84%
73.7%	69%	65%	84%	69%	80%	75%
61.5%	57%	67%	55%	59%	72%	59%
63.3%	63%	75%	52%	67%	67%	56%
71.7%	66%	75%	59%	70%	90%	70%
77.2%	77%	78%	78%	78%	74%	78%
55.2%	58%	33%	62%	64%	64%	50%
71.5%	74%	79%	69%	69%	69%	69%
48.5%	45%	45%	61%	45%	45%	50%
62.0%	62%	63%	58%	62%	50%	77%
80.7%	77%	72%	91%	77%	80%	87%
77.0%	80%	80%	74%	81%	65%	82%
72.3%	82%	82%	64%	73%	71%	62%
54.8%	68%	70%	45%	52%	44%	50%
35.8%	34%	100%	0%	28%	12%	41%
59.5%	67%	56%	63%	57%	56%	58%
58.5%	52%	52%	67%	52%	64%	64%
65.7%	68%	48%	75%	68%	67%	68%
51.5%	47%	52%	49%	54%	49%	58%
72.7%	70%	65%	82%	73%	75%	71%
73.3%	73%	87%	69%	79%	59%	73%
69.5%	75%	65%	72%	67%	70%	68%
79.7%	82%	90%	74%	76%	71%	85%
72.8%	88%	62%	70%	88%	70%	59%
68.8%	91%	73%	62%	82%	62%	43%
61.2%	67%	58%	74%	67%	41%	60%
72.8%	65%	70%	74%	80%	75%	73%
82.7%	85%	88%	85%	76%	77%	85%
49.5%	50%	47%	47%	55%	54%	44%
61.0%	74%	57%	56%	67%	56%	56%
52.8%	57%	47%	72%	47%	47%	47%
43.0%	47%	42%	48%	41%	40%	40%
67.8%	60%	59%	73%	70%	63%	82%
65.0%	66%	76%	74%	66%	55%	53%
68.0%	71%	43%	68%	71%	83%	72%
91.2%	92%	96%	92%	83%	92%	92%
63.2%	69%	65%	70%	75%	50%	50%
87.0%	90%	90%	81%	91%	90%	80%
54.0%	55%	46%	55%	58%	55%	55%