	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	1st 76.4%	4th 74.1%	6th 68.9%	2nd 76.2%	5th 72.9%	3rd 74.9%
65.0%	73%	62%	79%	59%	59%	58%
86.7%	91%	84%	85%	86%	82%	92%
87.7%	91%	87%	93%	95%	74%	86%
75.5%	77%	77%	73%	78%	69%	79%
62.5%	73%	50%	55%	57%	60%	80%
69.8%	63%	73%	63%	76%	77%	67%
84.0%	79%	93%	69%	85%	88%	90%
43.0%	66%	7%	47%	41%	59%	38%
68.2%	67%	56%	68%	78%	68%	72%
76.5%	79%	74%	69%	72%	83%	82%
73.5%	72%	80%	59%	71%	84%	75%
81.8%	83%	74%	84%	87%	85%	78%
51.0%	63%	81%	10%	63%	43%	46%
87.0%	93%	91%	92%	85%	71%	90%
86.0%	86%	87%	90%	83%	80%	90%
87.5%	91%	92%	81%	89%	79%	93%
76.2%	77%	81%	69%	82%	83%	65%
79.2%	77%	91%	77%	78%	75%	77%
50.2%	62%	46%	41%	56%	45%	51%
81.7%	83%	88%	77%	84%	82%	76%
87.7%	84%	90%	84%	95%	80%	93%
86.0%	88%	88%	72%	93%	91%	84%
54.2%	52%	54%	60%	43%	67%	49%
85.0%	93%	82%	85%	85%	85%	80%
82.0%	86%	87%	89%	80%	65%	85%
87.7%	94%	87%	87%	93%	72%	93%
86.5%	88%	79%	83%	83%	95%	91%
75.2%	77%	83%	64%	76%	80%	71%
75.0%	86%	79%	63%	84%	70%	68%
57.0%	62%	51%	54%	62%	53%	60%
71.0%	77%	63%	58%	78%	74%	76%
52.0%	53%	44%	37%	58%	58%	62%
76.5%	69%	79%	59%	80%	84%	88%
78.5%	77%	79%	73%	83%	76%	83%
35.3%	42%	32%	24%	37%	32%	45%
86.3%	66%	89%	97%	90%	89%	87%
75.2%	74%	84%	63%	77%	76%	77%
45.7%	50%	38%	41%	48%	49%	48%
87.3%	82%	87%	86%	91%	92%	86%
79.2%	73%	80%	81%	82%	87%	72%
80.7%	73%	91%	78%	81%	85%	76%
65.2%	70%	69%	50%	65%	73%	64%
68.2%	64%	69%	61%	75%	73%	67%
85.3%	94%	83%	91%	89%	77%	78%
81.3%	83%	76%	77%	83%	84%	85%
62.0%	66%	54%	55%	69%	58%	70%
43.3%	60%	39%	35%	50%	30%	46%
63.3%	67%	70%	49%	68%	68%	58%
84.3%	94%	94%	75%	75%	84%	84%
73.0%	81%	81%	65%	78%	57%	76%
87.7%	92%	89%	88%	90%	74%	93%
89.8%	92%	90%	87%	90%	93%	87%
92.5%	89%	98%	84%	97%	93%	94%
78.3%	82%	68%	87%	83%	68%	82%