	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 70.3%	1st 70.3%	6th 58.3%	3rd 68.7%	5th 65.1%	4th 66.9%
61.5%	75%	64%	62%	59%	60%	49%
65.7%	66%	59%	69%	66%	59%	75%
76.8%	78%	84%	81%	80%	70%	68%
58.8%	63%	69%	59%	57%	53%	52%
58.0%	76%	34%	49%	73%	36%	80%
64.3%	67%	67%	55%	68%	62%	67%
72.3%	78%	79%	53%	74%	75%	75%
55.7%	66%	100%	33%	39%	46%	50%
54.8%	60%	66%	38%	62%	53%	50%
61.0%	70%	69%	36%	63%	63%	65%
72.2%	80%	78%	51%	73%	75%	76%
80.7%	74%	65%	82%	81%	89%	93%
47.0%	61%	68%	10%	61%	41%	41%
79.7%	79%	81%	74%	82%	80%	82%
78.2%	73%	80%	87%	76%	71%	82%
83.8%	86%	82%	86%	86%	77%	86%
68.2%	73%	79%	60%	72%	69%	56%
73.0%	71%	75%	71%	75%	75%	71%
39.8%	48%	46%	28%	47%	24%	46%
75.2%	89%	77%	62%	77%	78%	68%
78.5%	84%	93%	55%	76%	87%	76%
62.5%	70%	73%	44%	64%	66%	58%
69.3%	72%	74%	76%	48%	92%	54%
64.3%	70%	60%	65%	66%	60%	65%
73.8%	68%	68%	85%	73%	65%	84%
75.7%	81%	89%	64%	78%	68%	74%
84.8%	86%	85%	80%	83%	92%	83%
66.2%	72%	81%	47%	67%	78%	52%
74.0%	81%	80%	53%	86%	78%	66%
38.0%	36%	45%	37%	43%	24%	43%
78.2%	83%	66%	65%	86%	83%	86%
63.5%	65%	64%	49%	69%	53%	81%
63.3%	72%	72%	35%	65%	70%	66%
71.3%	75%	75%	58%	74%	71%	75%
25.2%	21%	40%	18%	30%	16%	26%
89.2%	91%	87%	89%	91%	98%	79%
65.7%	70%	72%	53%	67%	66%	66%
37.8%	38%	46%	31%	41%	33%	38%
85.2%	85%	78%	87%	81%	86%	94%
72.0%	70%	82%	68%	70%	75%	67%
72.5%	73%	70%	71%	74%	75%	72%
62.3%	71%	72%	49%	54%	67%	61%
50.3%	56%	62%	36%	56%	49%	43%
80.8%	78%	86%	75%	78%	83%	85%
72.8%	78%	73%	59%	74%	76%	77%
44.2%	40%	50%	44%	40%	41%	50%
38.7%	46%	36%	27%	55%	24%	44%
48.7%	52%	54%	34%	58%	52%	42%
84.7%	96%	94%	63%	91%	86%	78%
67.3%	65%	69%	68%	83%	47%	72%
77.0%	81%	77%	84%	74%	69%	77%
83.7%	89%	73%	87%	81%	83%	89%
91.8%	93%	90%	89%	97%	90%	92%
56.0%	54%	38%	55%	67%	54%	68%