	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 64.4%	5th 60.6%	4th 61.2%	2nd 63.9%	6th 59.1%	3rd 61.9%
63.5%	68%	87%	48%	68%	67%	43%
47.5%	39%	81%	27%	52%	43%	43%
54.2%	54%	74%	51%	48%	54%	44%
53.8%	57%	41%	61%	51%	62%	51%
32.2%	33%	30%	37%	30%	26%	37%
74.7%	77%	37%	84%	82%	82%	86%
57.3%	55%	62%	58%	59%	57%	53%
73.7%	67%	59%	88%	84%	72%	72%
68.2%	74%	49%	65%	49%	79%	93%
68.3%	72%	63%	73%	72%	65%	65%
85.2%	82%	89%	81%	89%	85%	85%
74.8%	87%	72%	82%	82%	49%	77%
73.7%	71%	77%	77%	72%	77%	68%
48.3%	61%	49%	35%	58%	43%	44%
52.8%	56%	22%	55%	58%	63%	63%
52.0%	52%	63%	48%	57%	41%	51%
85.0%	84%	82%	90%	78%	88%	88%
47.3%	44%	55%	44%	42%	51%	48%
70.7%	63%	73%	81%	77%	53%	77%
55.0%	51%	58%	37%	58%	63%	63%
66.5%	71%	64%	68%	70%	55%	71%
65.7%	74%	58%	66%	68%	64%	64%
67.2%	56%	69%	65%	70%	75%	68%
40.7%	38%	77%	40%	27%	31%	31%
58.7%	61%	58%	67%	58%	57%	51%
68.3%	73%	68%	65%	68%	68%	68%
46.7%	53%	53%	41%	54%	38%	41%
68.0%	67%	77%	56%	77%	75%	56%
44.7%	48%	51%	41%	44%	51%	33%
55.5%	54%	49%	65%	66%	29%	70%
82.5%	77%	88%	79%	79%	86%	86%
58.2%	50%	54%	66%	65%	62%	52%
62.5%	63%	75%	60%	67%	57%	53%
51.2%	57%	68%	48%	52%	41%	41%
81.5%	87%	86%	75%	73%	84%	84%
67.7%	69%	81%	67%	63%	63%	63%
58.5%	67%	74%	47%	31%	62%	70%
65.0%	65%	61%	55%	74%	68%	67%
59.3%	66%	33%	64%	66%	63%	64%
58.2%	47%	46%	55%	60%	68%	73%
70.8%	74%	48%	87%	49%	93%	74%
32.3%	41%	13%	51%	30%	37%	22%
68.0%	72%	79%	65%	68%	62%	62%
61.0%	65%	68%	52%	51%	65%	65%
64.2%	60%	53%	60%	68%	72%	72%
72.2%	82%	76%	56%	83%	63%	73%
50.7%	62%	58%	45%	47%	45%	47%
94.5%	100%	88%	85%	100%	100%	94%
45.0%	66%	10%	59%	51%	42%	42%
47.2%	51%	50%	51%	47%	37%	47%
55.7%	60%	49%	56%	56%	57%	56%
48.7%	53%	30%	59%	50%	51%	49%
49.7%	46%	45%	59%	51%	41%	56%
53.7%	55%	74%	48%	48%	48%	49%
56.7%	53%	55%	66%	58%	56%	52%
50.0%	55%	63%	42%	50%	52%	38%
49.2%	42%	51%	41%	49%	40%	72%
55.8%	56%	57%	58%	58%	53%	53%
70.0%	77%	71%	67%	69%	62%	74%
39.5%	40%	13%	57%	48%	31%	48%
61.5%	67%	74%	59%	67%	56%	46%
59.3%	65%	73%	47%	62%	62%	47%
64.0%	62%	74%	70%	67%	50%	61%
50.7%	45%	46%	57%	57%	52%	47%
67.5%	72%	34%	77%	77%	74%	71%
61.0%	60%	58%	69%	63%	53%	63%
55.3%	60%	100%	40%	49%	49%	34%
57.7%	65%	58%	58%	69%	47%	49%
63.2%	66%	56%	62%	70%	60%	65%
77.3%	86%	69%	86%	72%	70%	81%
67.8%	65%	73%	71%	67%	66%	65%
71.3%	76%	58%	75%	73%	73%	73%
68.7%	76%	30%	78%	76%	76%	76%
54.0%	64%	51%	46%	66%	44%	53%
67.5%	67%	66%	66%	68%	71%	67%
69.8%	74%	48%	78%	74%	68%	77%
71.8%	81%	37%	85%	80%	63%	85%
60.8%	59%	70%	58%	66%	46%	66%
56.5%	58%	66%	57%	57%	56%	45%
56.2%	55%	55%	62%	54%	56%	55%
70.0%	72%	78%	68%	69%	63%	70%
79.7%	86%	89%	79%	89%	46%	89%
76.5%	81%	84%	78%	73%	70%	73%
67.8%	71%	73%	66%	73%	62%	62%
40.8%	33%	44%	51%	44%	25%	48%
60.0%	69%	26%	73%	65%	66%	61%
55.2%	58%	56%	50%	58%	49%	60%
64.2%	70%	39%	75%	68%	58%	75%
54.0%	61%	74%	36%	55%	43%	55%
74.3%	83%	83%	77%	77%	51%	75%
48.7%	44%	74%	36%	44%	58%	36%
42.0%	66%	76%	16%	46%	23%	25%
71.5%	74%	51%	67%	88%	65%	84%
73.5%	80%	75%	69%	73%	70%	74%
53.0%	60%	31%	60%	55%	54%	58%
71.3%	62%	71%	76%	73%	73%	73%
55.3%	56%	32%	60%	61%	62%	61%
75.0%	80%	69%	74%	82%	72%	73%
70.7%	78%	87%	50%	77%	66%	66%
74.0%	77%	67%	74%	67%	79%	80%
51.3%	55%	30%	55%	49%	58%	61%
78.8%	74%	68%	75%	80%	88%	88%
68.0%	77%	69%	72%	73%	73%	44%
72.0%	72%	82%	53%	77%	76%	72%
75.5%	87%	68%	71%	79%	59%	89%
65.5%	77%	33%	55%	87%	86%	55%
60.2%	82%	78%	41%	65%	46%	49%
43.8%	39%	53%	27%	47%	39%	58%
62.5%	56%	70%	56%	54%	58%	81%
57.0%	62%	66%	60%	54%	50%	50%
59.5%	60%	40%	73%	66%	59%	59%
67.7%	63%	63%	76%	75%	55%	74%
74.8%	72%	68%	68%	100%	68%	73%
57.8%	65%	41%	59%	65%	61%	56%
71.3%	74%	90%	71%	68%	51%	74%
71.0%	69%	72%	73%	76%	62%	74%