	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 68.9%	1st 69.9%	6th 61.7%	3rd 67.4%	5th 63.6%	4th 66.7%
72.0%	70%	71%	62%	79%	72%	78%
70.8%	63%	71%	74%	72%	73%	72%
71.0%	70%	70%	70%	76%	72%	68%
55.5%	54%	55%	54%	55%	47%	68%
93.2%	95%	91%	94%	91%	94%	94%
56.8%	65%	68%	47%	53%	55%	53%
78.3%	69%	86%	79%	76%	90%	70%
51.0%	49%	59%	34%	53%	58%	53%
81.0%	80%	88%	76%	80%	85%	77%
57.7%	62%	65%	53%	60%	43%	63%
87.7%	89%	89%	89%	92%	81%	86%
40.2%	45%	49%	31%	43%	26%	47%
80.3%	82%	82%	78%	83%	74%	83%
73.3%	78%	67%	74%	77%	64%	80%
67.0%	75%	63%	60%	65%	66%	73%
64.0%	67%	67%	54%	64%	67%	65%
52.2%	71%	57%	45%	53%	35%	52%
55.3%	64%	60%	36%	63%	60%	49%
61.0%	63%	62%	53%	59%	66%	63%
76.3%	63%	86%	86%	75%	72%	76%
72.7%	84%	75%	58%	75%	72%	72%
67.3%	77%	77%	52%	66%	63%	69%
62.8%	63%	72%	71%	69%	34%	68%
73.5%	82%	81%	67%	71%	65%	75%
69.5%	71%	68%	75%	69%	66%	68%
72.2%	68%	75%	67%	78%	63%	82%
52.7%	58%	58%	38%	54%	57%	51%
49.3%	61%	55%	38%	42%	58%	42%
44.8%	53%	44%	39%	57%	21%	55%
60.5%	61%	71%	59%	62%	53%	57%
56.7%	61%	55%	49%	56%	62%	57%
64.2%	68%	66%	64%	59%	62%	66%
52.8%	50%	51%	53%	57%	55%	51%
67.5%	56%	80%	73%	62%	73%	61%
67.3%	73%	62%	61%	68%	69%	71%
64.7%	72%	71%	55%	66%	65%	59%
68.3%	75%	60%	60%	68%	75%	72%
84.5%	90%	89%	93%	88%	75%	72%
43.0%	47%	53%	30%	42%	44%	42%
97.8%	98%	95%	98%	98%	100%	98%
62.7%	68%	73%	60%	64%	57%	54%
81.8%	78%	92%	76%	79%	78%	88%
72.0%	73%	77%	66%	78%	68%	70%