	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	1st 68.9%	2nd 65.4%	5th 61.1%	4th 64.0%	3rd 64.2%	6th 57.9%
43.2%	61%	39%	42%	46%	32%	39%
57.3%	66%	47%	57%	62%	56%	56%
85.3%	81%	78%	94%	88%	81%	90%
60.7%	63%	52%	52%	64%	68%	65%
72.3%	76%	44%	85%	66%	90%	73%
48.7%	46%	46%	62%	46%	46%	46%
69.2%	83%	73%	68%	80%	62%	49%
59.3%	72%	100%	51%	37%	59%	37%
51.0%	58%	44%	51%	49%	50%	54%
57.0%	61%	66%	53%	54%	65%	43%
45.5%	50%	53%	32%	52%	46%	40%
70.3%	75%	72%	75%	76%	63%	61%
50.7%	72%	77%	30%	59%	22%	44%
79.0%	90%	89%	68%	73%	93%	61%
66.2%	68%	72%	59%	67%	69%	62%
65.7%	69%	63%	69%	43%	75%	75%
68.2%	75%	69%	63%	73%	68%	61%
68.2%	72%	78%	50%	74%	77%	58%
69.5%	67%	81%	70%	55%	89%	55%
56.7%	61%	56%	52%	58%	58%	55%
70.3%	77%	60%	80%	68%	65%	72%
47.2%	57%	50%	39%	41%	58%	38%
50.2%	60%	61%	44%	35%	66%	35%
51.5%	62%	64%	42%	55%	43%	43%
71.2%	66%	68%	77%	77%	67%	72%
60.0%	61%	58%	69%	58%	53%	61%
90.2%	95%	86%	94%	90%	86%	90%
64.8%	79%	53%	70%	76%	47%	64%
62.8%	70%	64%	44%	70%	75%	54%
86.2%	89%	76%	100%	76%	100%	76%
54.7%	64%	51%	49%	58%	39%	67%
59.7%	60%	57%	50%	64%	77%	50%
55.7%	60%	72%	45%	43%	71%	43%
51.8%	54%	61%	49%	52%	54%	41%
40.7%	55%	54%	34%	36%	34%	31%
66.8%	70%	77%	59%	69%	63%	63%
66.0%	74%	79%	59%	74%	72%	38%
64.0%	67%	56%	66%	77%	67%	51%
60.3%	65%	59%	65%	59%	55%	59%
66.5%	70%	58%	70%	59%	71%	71%
66.7%	58%	89%	64%	63%	63%	63%
64.2%	74%	71%	61%	58%	75%	46%
64.5%	65%	88%	54%	54%	82%	44%
74.0%	76%	63%	86%	82%	64%	73%
45.2%	48%	44%	33%	49%	55%	42%
70.5%	63%	76%	58%	76%	76%	74%
63.8%	70%	64%	66%	64%	64%	55%
63.8%	82%	80%	50%	66%	66%	39%
90.3%	89%	88%	85%	100%	90%	90%
67.8%	72%	77%	71%	88%	33%	66%
72.5%	86%	74%	77%	71%	53%	74%
66.2%	62%	55%	64%	75%	72%	69%
81.7%	88%	74%	82%	86%	74%	86%
58.7%	68%	25%	61%	67%	66%	65%