	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 77.0%	1st 77.5%	6th 71.0%	4th 74.0%	3rd 74.8%	5th 72.8%
81.2%	76%	89%	69%	85%	89%	79%
81.8%	78%	67%	83%	83%	88%	92%
76.2%	72%	70%	85%	76%	78%	76%
57.3%	65%	61%	60%	51%	54%	53%
86.0%	85%	93%	76%	85%	89%	88%
79.0%	86%	93%	73%	78%	74%	70%
83.0%	79%	82%	86%	80%	95%	76%
60.8%	62%	69%	44%	62%	65%	63%
68.2%	63%	77%	59%	69%	73%	68%
52.7%	63%	56%	65%	50%	35%	47%
89.8%	88%	87%	93%	94%	90%	87%
46.7%	55%	53%	47%	44%	42%	39%
86.8%	91%	90%	84%	86%	82%	88%
88.7%	88%	88%	94%	92%	82%	88%
85.8%	87%	84%	82%	88%	91%	83%
70.0%	76%	77%	54%	71%	77%	65%
69.0%	73%	77%	74%	63%	72%	55%
58.0%	64%	68%	40%	56%	71%	49%
61.8%	67%	54%	49%	63%	63%	75%
82.2%	68%	90%	87%	86%	82%	80%
76.8%	87%	74%	63%	80%	80%	77%
76.5%	82%	82%	54%	82%	86%	73%
59.8%	63%	73%	66%	48%	44%	65%
86.0%	90%	91%	79%	82%	89%	85%
88.3%	89%	83%	90%	89%	92%	87%
74.7%	75%	77%	71%	78%	66%	81%
69.5%	76%	79%	53%	66%	75%	68%
73.7%	83%	91%	62%	69%	79%	58%
39.0%	48%	38%	45%	37%	18%	48%
64.5%	60%	64%	63%	65%	76%	59%
84.3%	87%	90%	80%	92%	72%	85%
83.5%	88%	88%	75%	84%	82%	84%
59.5%	61%	56%	69%	48%	59%	64%
78.5%	77%	90%	80%	74%	87%	63%
59.2%	70%	48%	55%	54%	57%	71%
78.8%	87%	69%	85%	81%	80%	71%
81.3%	88%	82%	77%	84%	80%	77%
93.0%	93%	91%	97%	98%	89%	90%
76.3%	81%	90%	64%	75%	80%	68%
95.8%	94%	91%	98%	95%	100%	97%
77.0%	83%	96%	70%	76%	73%	64%
80.3%	84%	84%	71%	75%	78%	90%
82.5%	81%	81%	82%	86%	81%	84%