	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 69.5%	1st 70.0%	5th 60.9%	3rd 68.7%	6th 60.4%	4th 68.1%
43.3%	40%	36%	49%	47%	34%	54%
64.0%	68%	73%	49%	61%	68%	65%
44.5%	56%	52%	32%	54%	32%	41%
70.2%	68%	73%	62%	72%	69%	77%
72.8%	83%	79%	62%	73%	65%	75%
78.2%	71%	88%	73%	77%	83%	77%
72.5%	76%	58%	73%	78%	75%	75%
74.7%	79%	76%	68%	79%	79%	67%
64.8%	67%	82%	57%	65%	51%	67%
79.7%	88%	88%	78%	84%	64%	76%
71.5%	82%	87%	76%	76%	38%	70%
56.2%	61%	50%	70%	58%	40%	58%
71.0%	84%	85%	65%	84%	39%	69%
75.0%	68%	83%	62%	77%	83%	77%
57.2%	66%	54%	55%	65%	43%	60%
45.5%	49%	58%	41%	38%	34%	53%
45.0%	51%	42%	40%	43%	51%	43%
69.7%	73%	68%	58%	71%	74%	74%
53.0%	54%	61%	38%	57%	55%	53%
64.7%	63%	72%	78%	72%	43%	60%
73.5%	69%	75%	64%	84%	65%	84%
65.2%	75%	54%	61%	70%	44%	87%
93.7%	96%	97%	94%	83%	93%	99%
68.7%	69%	72%	63%	66%	70%	72%
72.2%	83%	84%	68%	84%	42%	72%
64.0%	60%	78%	78%	62%	45%	61%
74.0%	78%	75%	80%	76%	72%	63%
67.7%	65%	67%	77%	70%	56%	71%
78.0%	87%	94%	10%	85%	94%	98%
49.2%	47%	59%	31%	47%	64%	47%
43.2%	43%	41%	51%	43%	31%	50%
58.3%	59%	55%	63%	59%	55%	59%
80.5%	79%	84%	80%	83%	74%	83%
66.8%	65%	79%	71%	65%	66%	55%
74.0%	83%	73%	71%	74%	72%	71%
86.0%	90%	87%	76%	88%	88%	87%
80.0%	84%	84%	84%	77%	70%	81%
50.0%	51%	43%	51%	49%	54%	52%
58.5%	61%	60%	60%	66%	44%	60%
69.0%	70%	74%	67%	74%	57%	72%
62.3%	64%	58%	57%	58%	70%	67%
65.8%	70%	68%	60%	65%	68%	64%
51.8%	55%	54%	41%	56%	54%	51%
71.8%	87%	87%	10%	91%	65%	91%
83.5%	85%	82%	82%	82%	87%	83%
67.7%	74%	72%	66%	72%	60%	62%