	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 80.1%	2nd 79.6%	6th 68.0%	3rd 75.9%	4th 71.4%	5th 71.0%
50.0%	54%	51%	56%	53%	46%	40%
85.7%	92%	95%	83%	87%	81%	76%
82.8%	79%	88%	90%	93%	76%	71%
67.8%	73%	69%	62%	66%	66%	71%
63.5%	84%	37%	73%	60%	63%	64%
72.5%	84%	83%	82%	85%	45%	56%
75.2%	87%	74%	63%	73%	81%	73%
58.7%	67%	95%	53%	38%	57%	42%
69.2%	67%	76%	58%	78%	64%	72%
65.8%	78%	62%	48%	71%	70%	66%
85.3%	97%	93%	63%	94%	70%	95%
81.5%	77%	64%	89%	88%	82%	89%
56.5%	65%	81%	38%	65%	45%	45%
79.7%	88%	84%	69%	74%	88%	75%
75.0%	87%	77%	66%	73%	80%	67%
88.0%	94%	94%	90%	89%	81%	80%
68.3%	77%	64%	62%	79%	69%	59%
67.2%	75%	74%	59%	80%	45%	70%
82.5%	84%	88%	85%	68%	85%	85%
66.3%	79%	69%	58%	66%	70%	56%
76.5%	79%	92%	63%	73%	76%	76%
79.8%	92%	91%	61%	88%	82%	65%
56.3%	70%	61%	55%	42%	63%	47%
72.8%	86%	64%	70%	81%	69%	67%
78.8%	86%	88%	66%	76%	79%	78%
85.3%	86%	88%	81%	88%	84%	85%
91.7%	96%	86%	81%	94%	99%	94%
67.0%	88%	88%	48%	63%	60%	55%
73.0%	85%	81%	50%	86%	66%	70%
86.8%	87%	87%	86%	87%	87%	87%
56.2%	45%	83%	43%	54%	48%	64%
79.7%	85%	82%	69%	89%	69%	84%
62.5%	71%	66%	46%	65%	64%	63%
76.7%	77%	83%	70%	79%	71%	80%
57.2%	59%	92%	59%	57%	46%	30%
81.8%	85%	85%	79%	82%	80%	80%
70.5%	76%	80%	57%	71%	71%	68%
77.2%	77%	84%	69%	83%	76%	74%
80.5%	77%	72%	82%	86%	82%	84%
84.8%	82%	89%	78%	82%	88%	90%
80.3%	78%	84%	78%	83%	79%	80%
62.8%	71%	72%	51%	58%	64%	61%
67.5%	76%	83%	65%	67%	54%	60%
89.5%	97%	93%	85%	92%	92%	78%
74.0%	81%	75%	65%	69%	76%	78%
87.5%	85%	91%	81%	92%	87%	89%
67.2%	86%	77%	54%	53%	77%	56%
61.8%	71%	76%	47%	56%	67%	54%
77.5%	84%	85%	80%	80%	68%	68%
75.3%	71%	81%	88%	86%	53%	73%
84.7%	83%	87%	85%	87%	78%	88%
84.5%	84%	81%	82%	85%	84%	91%
83.0%	89%	76%	81%	92%	79%	81%
80.5%	91%	76%	70%	91%	71%	84%