	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 72.4%	1st 72.8%	6th 65.1%	3rd 71.0%	5th 67.1%	4th 68.1%
56.8%	67%	48%	57%	60%	62%	47%
62.7%	66%	56%	64%	63%	56%	71%
83.5%	85%	89%	88%	89%	74%	76%
64.3%	63%	74%	65%	61%	64%	59%
69.8%	80%	64%	67%	68%	63%	77%
72.0%	65%	73%	67%	78%	76%	73%
62.0%	71%	65%	47%	65%	65%	59%
61.3%	77%	100%	43%	38%	72%	38%
66.3%	70%	79%	53%	74%	62%	60%
71.3%	74%	76%	59%	74%	75%	70%
78.0%	76%	83%	79%	78%	75%	77%
87.2%	87%	77%	93%	92%	84%	90%
47.2%	61%	75%	10%	55%	41%	41%
71.0%	77%	82%	77%	68%	51%	71%
70.2%	71%	72%	78%	71%	60%	69%
72.0%	81%	64%	68%	74%	64%	81%
58.2%	59%	65%	51%	60%	61%	53%
79.5%	75%	88%	67%	86%	79%	82%
61.5%	71%	62%	52%	69%	53%	62%
81.7%	85%	84%	77%	81%	88%	75%
75.5%	79%	74%	81%	78%	63%	78%
82.8%	93%	82%	75%	88%	86%	73%
53.2%	49%	58%	57%	39%	73%	43%
77.0%	79%	75%	81%	71%	78%	78%
72.0%	75%	86%	79%	68%	52%	72%
77.8%	82%	81%	87%	81%	58%	78%
94.3%	95%	96%	97%	95%	90%	93%
80.8%	80%	86%	70%	90%	85%	74%
63.0%	69%	72%	57%	71%	53%	56%
52.5%	51%	53%	57%	51%	44%	59%
48.7%	49%	60%	33%	46%	58%	46%
65.0%	60%	47%	58%	63%	80%	82%
65.3%	72%	72%	55%	65%	66%	62%
66.0%	69%	71%	57%	67%	66%	66%
41.8%	48%	44%	38%	36%	39%	46%
82.7%	86%	76%	84%	81%	81%	88%
85.5%	88%	94%	71%	88%	87%	85%
52.2%	51%	54%	48%	58%	56%	46%
76.2%	73%	78%	74%	79%	74%	79%
86.2%	85%	82%	87%	88%	89%	86%
86.5%	91%	89%	89%	87%	85%	78%
58.7%	66%	66%	47%	54%	65%	54%
63.7%	65%	79%	56%	75%	51%	56%
66.2%	67%	62%	83%	72%	61%	52%
88.2%	92%	88%	72%	97%	90%	90%
53.2%	49%	52%	56%	55%	50%	57%
40.5%	51%	48%	29%	49%	21%	45%
60.0%	70%	66%	39%	67%	63%	55%
75.7%	83%	89%	57%	75%	82%	68%
75.0%	78%	80%	71%	85%	57%	79%
77.8%	85%	77%	83%	80%	60%	82%
80.5%	75%	82%	77%	81%	90%	78%
87.7%	86%	82%	86%	86%	88%	98%
59.8%	59%	54%	60%	65%	55%	66%