	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 63.7%	1st 66.8%	6th 52.4%	3rd 62.8%	4th 62.6%	5th 61.3%
60.3%	78%	57%	64%	63%	48%	52%
85.8%	88%	80%	87%	89%	93%	78%
78.3%	83%	79%	79%	85%	74%	70%
73.3%	76%	75%	70%	81%	69%	69%
31.7%	33%	22%	22%	32%	33%	48%
55.8%	59%	53%	39%	62%	69%	53%
65.8%	73%	72%	49%	64%	70%	67%
57.3%	74%	100%	34%	37%	55%	44%
63.8%	69%	61%	52%	76%	66%	59%
51.2%	52%	67%	28%	48%	66%	46%
64.3%	68%	75%	43%	57%	71%	72%
76.8%	75%	74%	82%	79%	72%	79%
45.8%	61%	69%	10%	53%	41%	41%
85.0%	83%	89%	90%	83%	83%	82%
78.7%	87%	81%	68%	82%	74%	80%
79.3%	75%	81%	78%	80%	87%	75%
72.7%	73%	74%	70%	74%	76%	69%
64.2%	63%	84%	54%	63%	66%	55%
26.2%	26%	38%	15%	30%	21%	27%
67.2%	69%	73%	49%	73%	74%	65%
73.7%	69%	80%	56%	78%	81%	78%
69.3%	82%	73%	46%	67%	81%	67%
39.5%	44%	42%	42%	32%	44%	33%
72.2%	76%	88%	54%	76%	67%	72%
84.8%	86%	83%	85%	87%	82%	86%
81.2%	83%	90%	66%	76%	87%	85%
82.0%	86%	77%	73%	81%	89%	86%
61.0%	64%	71%	49%	61%	66%	55%
71.8%	81%	89%	44%	82%	69%	66%
31.8%	29%	39%	28%	32%	24%	39%
52.0%	48%	42%	52%	58%	52%	60%
34.2%	22%	32%	19%	39%	40%	53%
48.2%	48%	55%	27%	50%	59%	50%
68.2%	68%	73%	59%	69%	68%	72%
20.3%	14%	25%	19%	24%	20%	20%
81.7%	79%	92%	81%	86%	74%	78%
60.8%	64%	73%	40%	62%	64%	62%
27.0%	27%	33%	23%	26%	27%	26%
83.0%	89%	75%	84%	80%	87%	83%
62.7%	58%	72%	56%	67%	71%	52%
76.2%	76%	87%	71%	76%	78%	69%
51.3%	59%	59%	35%	43%	64%	48%
45.3%	38%	52%	42%	50%	45%	45%
76.7%	83%	81%	82%	70%	70%	74%
61.7%	61%	61%	54%	61%	66%	67%
37.7%	34%	38%	36%	38%	32%	48%
29.3%	28%	29%	20%	37%	25%	37%
49.0%	53%	53%	30%	58%	50%	50%
56.3%	64%	70%	45%	57%	51%	51%
62.3%	65%	65%	59%	60%	52%	73%
76.3%	78%	89%	62%	68%	81%	80%
81.0%	82%	75%	84%	83%	80%	82%
81.7%	88%	89%	75%	89%	73%	76%
51.5%	50%	49%	48%	55%	52%	55%