	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 68.1%	1st 70.0%	6th 56.7%	3rd 66.6%	4th 66.0%	5th 63.3%
70.7%	82%	73%	50%	74%	75%	70%
81.0%	87%	75%	83%	83%	78%	80%
77.3%	71%	82%	80%	80%	77%	74%
39.5%	34%	40%	46%	37%	31%	49%
81.8%	84%	73%	82%	84%	88%	80%
56.5%	59%	72%	41%	59%	61%	47%
59.5%	56%	64%	59%	62%	67%	49%
49.7%	53%	59%	27%	47%	66%	46%
66.3%	68%	75%	46%	64%	72%	73%
34.5%	38%	36%	34%	36%	26%	37%
78.7%	86%	81%	86%	73%	74%	72%
29.2%	37%	34%	19%	34%	18%	33%
75.0%	80%	80%	61%	70%	82%	77%
79.7%	81%	80%	77%	79%	91%	70%
87.5%	89%	88%	85%	88%	88%	87%
66.0%	76%	81%	39%	67%	70%	63%
52.3%	61%	65%	47%	51%	45%	45%
49.7%	58%	56%	30%	53%	54%	47%
54.2%	64%	46%	48%	58%	48%	61%
64.5%	58%	74%	63%	64%	74%	54%
66.8%	78%	67%	43%	67%	83%	63%
73.3%	71%	83%	56%	76%	78%	76%
61.8%	69%	68%	58%	60%	45%	71%
72.2%	73%	82%	58%	69%	77%	74%
85.0%	85%	81%	84%	93%	87%	80%
74.8%	76%	81%	61%	79%	75%	77%
50.2%	60%	61%	32%	43%	61%	44%
62.5%	75%	71%	40%	64%	73%	52%
32.8%	35%	37%	23%	40%	19%	43%
43.3%	37%	50%	40%	48%	42%	43%
79.8%	84%	84%	76%	81%	75%	79%
82.3%	94%	71%	80%	80%	83%	86%
64.8%	59%	70%	67%	67%	64%	62%
66.5%	63%	89%	58%	66%	65%	58%
34.3%	40%	25%	29%	33%	34%	45%
69.0%	74%	84%	54%	77%	67%	58%
83.0%	89%	82%	79%	86%	76%	86%
83.7%	90%	79%	87%	88%	85%	73%
69.3%	67%	75%	52%	75%	82%	65%
93.8%	83%	99%	98%	97%	94%	92%
59.7%	58%	84%	45%	65%	56%	50%
68.8%	73%	69%	57%	71%	73%	70%
69.5%	75%	86%	60%	75%	60%	61%