	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 66.1%	1st 66.3%	5th 59.8%	3rd 63.5%	4th 62.0%	6th 56.6%
41.3%	61%	39%	50%	38%	24%	36%
52.7%	55%	67%	56%	62%	29%	47%
81.8%	81%	78%	94%	88%	77%	73%
59.2%	71%	54%	44%	62%	64%	60%
66.3%	65%	44%	81%	72%	60%	76%
48.7%	46%	46%	62%	46%	46%	46%
68.3%	80%	75%	55%	76%	71%	53%
59.2%	72%	100%	51%	37%	51%	44%
50.0%	58%	44%	46%	55%	48%	49%
57.8%	61%	66%	53%	55%	65%	47%
48.3%	50%	49%	40%	60%	46%	45%
70.3%	75%	72%	73%	76%	63%	63%
52.2%	72%	84%	41%	59%	13%	44%
76.7%	72%	76%	73%	73%	93%	73%
66.8%	69%	67%	59%	72%	69%	65%
48.7%	45%	53%	55%	43%	53%	43%
67.3%	70%	65%	62%	76%	67%	64%
62.2%	65%	78%	44%	74%	54%	58%
78.8%	74%	80%	74%	79%	89%	77%
56.2%	58%	56%	52%	58%	58%	55%
72.0%	76%	77%	74%	68%	65%	72%
51.0%	58%	60%	47%	37%	65%	39%
52.5%	60%	68%	44%	34%	74%	35%
49.5%	59%	67%	43%	48%	43%	37%
73.7%	67%	71%	77%	77%	67%	83%
62.5%	64%	68%	69%	58%	55%	61%
88.8%	95%	93%	88%	91%	95%	71%
72.5%	76%	77%	66%	76%	76%	64%
62.5%	73%	77%	44%	70%	62%	49%
76.8%	77%	83%	77%	89%	76%	59%
53.8%	55%	67%	41%	48%	45%	67%
52.8%	53%	39%	47%	64%	56%	58%
58.0%	60%	65%	45%	62%	71%	45%
49.5%	56%	51%	48%	52%	51%	39%
40.2%	60%	29%	49%	27%	49%	27%
59.5%	47%	70%	68%	53%	71%	48%
70.0%	74%	80%	56%	74%	72%	64%
58.5%	73%	52%	63%	56%	60%	47%
60.8%	65%	61%	67%	59%	54%	59%
57.0%	56%	66%	55%	57%	57%	51%
57.8%	63%	78%	52%	53%	68%	33%
59.8%	62%	70%	45%	62%	73%	47%
59.8%	58%	73%	49%	56%	73%	50%
73.7%	76%	59%	89%	82%	50%	86%
42.5%	52%	44%	33%	55%	29%	42%
67.0%	63%	74%	58%	76%	76%	55%
63.0%	66%	70%	59%	64%	64%	55%
58.2%	62%	76%	45%	54%	71%	41%
91.2%	89%	88%	100%	100%	80%	90%
73.2%	77%	73%	77%	75%	64%	73%
75.8%	67%	83%	70%	71%	78%	86%
69.8%	64%	59%	79%	69%	75%	73%
85.8%	95%	86%	82%	86%	80%	86%
56.0%	69%	33%	56%	67%	65%	46%