	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 76.3%	4th 72.3%	6th 70.7%	1st 77.1%	5th 71.0%	3rd 74.1%
78.7%	89%	60%	73%	86%	83%	81%
71.2%	63%	50%	76%	82%	81%	75%
50.0%	50%	44%	57%	51%	47%	51%
78.0%	73%	86%	82%	77%	86%	64%
85.0%	91%	86%	75%	88%	82%	88%
85.5%	85%	91%	91%	85%	77%	84%
85.5%	88%	84%	87%	86%	84%	84%
70.3%	78%	83%	48%	77%	74%	62%
71.7%	76%	75%	53%	80%	70%	76%
83.5%	79%	86%	86%	86%	78%	86%
73.2%	80%	65%	83%	72%	75%	64%
70.0%	73%	73%	70%	73%	68%	63%
74.0%	74%	82%	75%	73%	59%	81%
76.8%	80%	81%	70%	82%	70%	78%
75.2%	71%	78%	74%	81%	70%	77%
81.2%	83%	62%	82%	88%	89%	83%
78.5%	74%	82%	75%	87%	76%	77%
61.8%	67%	83%	44%	60%	59%	58%
43.7%	40%	57%	34%	40%	35%	56%
71.3%	79%	72%	64%	80%	67%	66%
73.8%	75%	81%	67%	78%	68%	74%
70.3%	77%	81%	61%	63%	75%	65%
63.3%	54%	74%	75%	56%	44%	77%
67.0%	75%	48%	69%	85%	51%	74%
78.7%	87%	85%	75%	82%	68%	75%
73.3%	76%	63%	78%	77%	73%	73%
64.8%	74%	84%	51%	53%	70%	57%
71.8%	76%	69%	61%	74%	77%	74%
65.7%	78%	82%	59%	61%	63%	51%
73.3%	84%	68%	66%	80%	71%	71%
70.2%	71%	42%	76%	81%	72%	79%
89.5%	95%	98%	86%	86%	78%	94%
62.0%	61%	55%	70%	71%	52%	63%
66.8%	68%	73%	59%	67%	67%	67%
63.5%	84%	34%	61%	78%	62%	62%
63.0%	59%	60%	72%	68%	61%	58%
83.0%	72%	78%	83%	90%	81%	94%
85.8%	88%	94%	81%	89%	75%	88%
81.2%	83%	64%	80%	88%	86%	86%
93.2%	96%	89%	96%	96%	85%	97%
71.0%	75%	51%	73%	76%	73%	78%
81.8%	88%	84%	60%	88%	80%	91%
86.0%	91%	72%	83%	94%	91%	85%