	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 65.2%	1st 67.6%	6th 58.3%	3rd 65.0%	5th 60.7%	4th 63.2%
58.5%	63%	63%	46%	59%	63%	57%
71.0%	62%	61%	65%	76%	82%	80%
90.3%	89%	95%	92%	89%	91%	86%
49.2%	46%	57%	44%	44%	39%	65%
62.5%	63%	68%	61%	62%	62%	59%
52.8%	65%	70%	32%	49%	51%	50%
72.7%	68%	86%	69%	62%	83%	68%
44.2%	42%	54%	32%	41%	51%	45%
70.0%	71%	72%	57%	73%	71%	76%
31.8%	30%	38%	28%	34%	16%	45%
67.7%	74%	73%	72%	75%	56%	56%
39.3%	41%	44%	32%	36%	36%	47%
65.0%	61%	62%	72%	68%	60%	67%
85.2%	88%	79%	81%	93%	79%	91%
80.8%	83%	81%	92%	92%	56%	81%
56.5%	61%	58%	44%	63%	58%	55%
45.7%	57%	59%	33%	43%	41%	41%
62.3%	72%	71%	46%	71%	60%	54%
49.0%	66%	37%	10%	62%	55%	64%
81.7%	73%	94%	82%	70%	95%	76%
63.7%	69%	69%	61%	62%	58%	63%
49.8%	53%	58%	32%	52%	57%	47%
61.3%	61%	67%	63%	67%	50%	60%
60.3%	63%	59%	63%	66%	47%	64%
81.8%	85%	85%	82%	80%	75%	84%
53.7%	51%	55%	47%	60%	54%	55%
54.8%	61%	62%	36%	51%	70%	49%
56.0%	63%	60%	59%	48%	57%	49%
50.0%	54%	59%	41%	57%	33%	56%
58.2%	48%	85%	57%	58%	58%	43%
69.8%	72%	77%	74%	61%	67%	68%
65.0%	67%	61%	64%	63%	65%	70%
71.8%	70%	76%	73%	74%	72%	66%
61.3%	63%	70%	53%	68%	59%	55%
49.2%	60%	50%	37%	52%	42%	54%
58.3%	62%	57%	60%	61%	57%	53%
77.3%	83%	75%	75%	75%	75%	81%
78.8%	85%	79%	91%	85%	66%	67%
62.5%	63%	61%	63%	63%	64%	61%
90.7%	89%	95%	92%	91%	91%	86%
72.5%	69%	77%	74%	77%	69%	69%
70.3%	67%	77%	56%	81%	66%	75%
69.5%	72%	70%	63%	79%	54%	79%