	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 74.9%	1st 77.3%	6th 59.8%	3rd 71.8%	5th 69.3%	4th 70.2%
52.2%	53%	53%	55%	53%	55%	44%
85.0%	83%	82%	89%	87%	77%	92%
83.3%	92%	82%	94%	83%	78%	71%
70.5%	72%	73%	71%	68%	68%	71%
61.2%	70%	59%	47%	57%	57%	77%
71.0%	78%	78%	55%	81%	66%	68%
77.8%	86%	81%	57%	81%	79%	83%
56.5%	67%	95%	37%	45%	57%	38%
73.3%	75%	95%	55%	78%	66%	71%
66.3%	74%	81%	35%	65%	75%	68%
88.3%	89%	97%	64%	89%	94%	97%
80.3%	84%	63%	76%	85%	89%	85%
50.7%	65%	81%	10%	58%	45%	45%
82.2%	90%	89%	63%	82%	86%	83%
74.2%	84%	86%	56%	75%	73%	71%
85.2%	90%	79%	92%	82%	80%	88%
69.2%	73%	79%	52%	77%	71%	63%
71.5%	70%	87%	68%	67%	66%	71%
49.0%	54%	66%	40%	50%	32%	52%
65.0%	72%	77%	50%	64%	71%	56%
77.8%	84%	82%	57%	77%	89%	78%
75.5%	90%	87%	49%	77%	82%	68%
51.8%	59%	48%	58%	45%	55%	46%
75.5%	82%	77%	68%	80%	76%	70%
80.0%	85%	91%	60%	85%	80%	79%
83.0%	88%	85%	73%	80%	86%	86%
94.7%	98%	86%	97%	97%	97%	93%
65.3%	78%	92%	37%	63%	67%	55%
73.2%	83%	79%	56%	80%	71%	70%
44.5%	41%	50%	45%	51%	28%	52%
64.7%	71%	66%	53%	72%	67%	59%
62.8%	61%	70%	44%	66%	61%	75%
61.3%	69%	84%	32%	55%	67%	61%
76.8%	76%	70%	68%	83%	82%	82%
35.2%	25%	46%	22%	38%	38%	42%
84.2%	85%	83%	86%	83%	80%	88%
74.2%	79%	80%	61%	75%	74%	76%
43.8%	42%	57%	34%	44%	43%	43%
85.8%	90%	86%	80%	82%	88%	89%
85.0%	84%	93%	85%	79%	90%	79%
82.8%	82%	81%	84%	85%	86%	79%
62.0%	70%	70%	48%	62%	67%	55%
66.0%	67%	84%	60%	65%	58%	62%
89.2%	89%	95%	85%	91%	92%	83%
73.2%	77%	73%	62%	74%	75%	78%
55.8%	49%	59%	53%	56%	49%	69%
47.0%	47%	64%	33%	59%	30%	49%
63.0%	74%	75%	44%	63%	64%	58%
70.2%	81%	85%	57%	70%	62%	66%
73.7%	82%	84%	68%	83%	49%	76%
77.8%	83%	87%	68%	77%	71%	81%
84.0%	84%	77%	86%	81%	87%	89%
83.2%	90%	82%	79%	88%	79%	81%
73.8%	80%	63%	71%	82%	69%	78%