	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 67.4%	2nd 63.6%	6th 57.8%	4th 63.0%	5th 60.5%	3rd 63.1%
57.8%	72%	56%	67%	53%	46%	53%
51.7%	56%	49%	49%	49%	52%	55%
83.8%	84%	97%	86%	90%	74%	72%
58.3%	61%	61%	62%	49%	55%	62%
48.5%	60%	28%	45%	53%	39%	66%
62.5%	56%	68%	38%	68%	79%	66%
67.3%	73%	75%	52%	71%	73%	60%
42.8%	65%	37%	37%	37%	51%	30%
53.3%	55%	61%	43%	53%	53%	55%
54.7%	65%	55%	49%	49%	57%	53%
86.7%	83%	90%	78%	84%	90%	95%
73.0%	77%	64%	76%	71%	74%	76%
50.0%	74%	83%	10%	53%	31%	49%
72.3%	80%	69%	74%	74%	65%	72%
51.0%	56%	51%	51%	51%	49%	48%
67.3%	67%	59%	72%	67%	67%	72%
59.8%	60%	56%	59%	62%	67%	55%
67.5%	72%	82%	63%	72%	60%	56%
39.2%	54%	38%	30%	36%	28%	49%
80.8%	86%	82%	77%	85%	72%	83%
72.3%	77%	73%	67%	76%	71%	70%
73.5%	80%	72%	63%	80%	71%	75%
50.8%	53%	61%	53%	39%	59%	40%
72.3%	77%	68%	68%	71%	75%	75%
66.3%	76%	69%	58%	66%	62%	67%
68.5%	68%	68%	69%	72%	64%	70%
86.2%	81%	79%	94%	87%	88%	88%
63.2%	78%	72%	50%	59%	65%	55%
51.7%	61%	55%	38%	56%	50%	50%
40.7%	47%	39%	38%	40%	30%	50%
52.0%	54%	55%	40%	54%	61%	48%
47.7%	45%	34%	42%	46%	60%	59%
58.5%	58%	64%	46%	57%	64%	62%
80.7%	82%	85%	76%	78%	83%	80%
30.5%	29%	30%	22%	32%	33%	37%
67.0%	72%	70%	60%	66%	61%	73%
66.2%	66%	70%	56%	65%	70%	70%
46.3%	47%	44%	43%	47%	49%	48%
74.2%	73%	74%	79%	74%	72%	73%
86.0%	87%	88%	90%	87%	84%	80%
59.3%	59%	51%	66%	64%	55%	61%
81.3%	91%	85%	70%	77%	85%	80%
56.0%	59%	66%	45%	62%	52%	52%
69.0%	68%	72%	83%	68%	61%	62%
72.3%	77%	73%	58%	82%	62%	82%
47.5%	55%	41%	38%	54%	41%	56%
38.3%	56%	44%	30%	36%	18%	46%
63.8%	75%	70%	47%	67%	70%	54%
77.5%	84%	83%	71%	71%	83%	73%
74.5%	79%	74%	80%	82%	53%	79%
73.3%	82%	74%	77%	72%	63%	72%
68.0%	70%	63%	71%	70%	67%	67%
62.5%	61%	64%	62%	62%	56%	70%
52.8%	56%	46%	54%	57%	46%	58%