	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 66.3%	1st 68.1%	6th 55.9%	3rd 64.8%	5th 61.1%	4th 62.8%
58.7%	71%	59%	64%	64%	47%	47%
69.5%	70%	74%	74%	69%	60%	70%
85.8%	84%	87%	88%	92%	82%	82%
70.7%	83%	64%	63%	72%	68%	74%
45.2%	58%	28%	44%	50%	28%	63%
59.3%	61%	64%	42%	67%	58%	64%
66.7%	71%	66%	49%	71%	75%	68%
57.3%	65%	100%	40%	40%	59%	40%
58.8%	61%	65%	63%	57%	47%	60%
70.0%	69%	86%	44%	68%	86%	67%
88.5%	93%	92%	67%	93%	96%	90%
80.0%	79%	67%	76%	84%	85%	89%
50.7%	72%	69%	10%	72%	30%	51%
61.3%	69%	56%	55%	63%	63%	62%
52.7%	60%	46%	50%	49%	56%	55%
65.3%	67%	65%	71%	66%	57%	66%
76.3%	84%	82%	68%	78%	78%	68%
56.5%	57%	80%	48%	55%	52%	47%
30.7%	34%	39%	24%	34%	23%	30%
61.0%	67%	75%	43%	53%	64%	64%
74.2%	80%	84%	59%	75%	72%	75%
81.8%	87%	84%	68%	84%	86%	82%
58.5%	60%	54%	56%	49%	88%	44%
57.7%	62%	73%	42%	59%	54%	56%
65.7%	71%	72%	58%	61%	69%	63%
66.3%	71%	66%	57%	67%	69%	68%
88.8%	89%	84%	94%	90%	85%	91%
45.3%	54%	56%	29%	41%	57%	35%
72.2%	82%	82%	53%	78%	67%	71%
49.3%	50%	58%	44%	58%	37%	49%
59.3%	65%	55%	58%	68%	44%	66%
59.2%	56%	58%	55%	67%	50%	69%
69.0%	69%	80%	59%	74%	55%	77%
72.0%	77%	76%	57%	72%	74%	76%
40.8%	31%	54%	38%	50%	35%	37%
71.3%	56%	79%	81%	74%	69%	69%
61.2%	65%	67%	46%	61%	67%	61%
48.2%	57%	56%	48%	50%	37%	41%
66.2%	60%	69%	61%	75%	69%	63%
59.8%	56%	63%	59%	55%	72%	54%
59.3%	58%	62%	56%	60%	64%	56%
63.5%	66%	72%	50%	62%	67%	64%
63.7%	56%	75%	62%	67%	60%	62%
78.0%	85%	89%	83%	81%	65%	65%
63.7%	63%	72%	54%	66%	61%	66%
56.7%	54%	53%	52%	63%	55%	63%
42.5%	49%	41%	38%	52%	23%	52%
49.3%	61%	57%	29%	43%	62%	44%
57.3%	65%	72%	48%	53%	51%	55%
56.0%	61%	67%	58%	55%	35%	60%
75.7%	84%	77%	75%	72%	66%	80%
69.7%	70%	70%	65%	70%	76%	67%
78.8%	76%	80%	76%	80%	76%	85%
65.8%	60%	57%	70%	71%	68%	69%