	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 81.5%	1st 81.5%	5th 73.9%	3rd 78.8%	6th 72.8%	4th 75.5%
56.5%	60%	54%	63%	54%	62%	46%
76.7%	81%	78%	67%	78%	73%	83%
81.3%	84%	86%	91%	89%	69%	69%
74.7%	81%	78%	73%	79%	62%	75%
80.7%	85%	58%	91%	73%	85%	92%
75.8%	89%	84%	85%	84%	61%	52%
88.2%	95%	88%	76%	96%	85%	89%
59.7%	67%	96%	57%	38%	55%	45%
63.2%	65%	69%	62%	67%	55%	61%
77.8%	84%	79%	70%	81%	79%	74%
89.0%	88%	98%	72%	99%	80%	97%
89.5%	93%	92%	88%	84%	90%	90%
54.2%	65%	76%	44%	59%	40%	41%
87.2%	88%	85%	87%	91%	82%	90%
84.7%	87%	85%	80%	89%	84%	83%
83.2%	84%	89%	74%	91%	75%	86%
74.8%	80%	84%	57%	82%	72%	74%
77.2%	82%	91%	63%	83%	65%	79%
87.2%	90%	88%	89%	85%	83%	88%
72.5%	74%	77%	72%	73%	77%	62%
85.7%	85%	86%	84%	86%	83%	90%
86.8%	92%	89%	79%	86%	88%	87%
56.3%	69%	58%	53%	37%	73%	48%
78.2%	88%	78%	75%	84%	73%	71%
84.3%	84%	88%	88%	87%	75%	84%
89.2%	97%	89%	95%	91%	72%	91%
91.7%	95%	95%	93%	86%	93%	88%
71.5%	81%	87%	54%	75%	70%	62%
79.0%	88%	86%	59%	88%	80%	73%
84.7%	87%	83%	86%	84%	89%	79%
45.8%	43%	74%	42%	47%	22%	47%
81.7%	83%	79%	67%	91%	81%	89%
78.5%	84%	75%	66%	84%	81%	81%
79.7%	79%	83%	78%	79%	79%	80%
64.2%	64%	89%	62%	53%	60%	57%
85.8%	79%	90%	88%	85%	85%	88%
75.7%	85%	83%	68%	80%	62%	76%
76.5%	81%	81%	76%	73%	72%	76%
84.5%	80%	77%	90%	88%	85%	87%
77.0%	82%	88%	74%	84%	54%	80%
85.7%	90%	82%	78%	89%	92%	83%
66.8%	75%	74%	57%	61%	72%	62%
75.0%	84%	90%	65%	72%	64%	75%
83.7%	94%	81%	90%	91%	77%	69%
79.0%	80%	84%	82%	72%	84%	72%
85.0%	80%	91%	85%	89%	83%	82%
63.7%	81%	81%	58%	60%	50%	52%
60.3%	67%	66%	50%	59%	59%	61%
80.5%	84%	77%	83%	82%	79%	78%
74.2%	66%	88%	80%	81%	47%	83%
86.5%	89%	85%	90%	92%	72%	91%
88.5%	88%	86%	87%	89%	89%	92%
88.3%	88%	80%	89%	91%	91%	91%
68.5%	85%	43%	56%	86%	63%	78%