	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 64.3%	1st 66.1%	6th 57.6%	3rd 63.4%	5th 60.9%	4th 62.9%
40.8%	39%	42%	35%	40%	49%	40%
59.5%	61%	74%	55%	54%	63%	50%
62.7%	55%	71%	61%	57%	72%	60%
49.5%	62%	56%	36%	38%	56%	49%
73.5%	80%	83%	74%	80%	62%	62%
73.8%	80%	77%	79%	79%	63%	65%
40.3%	42%	43%	33%	42%	34%	48%
61.7%	71%	60%	49%	66%	62%	62%
64.7%	59%	95%	10%	71%	86%	67%
63.2%	71%	69%	68%	55%	49%	67%
65.3%	64%	68%	63%	69%	63%	65%
76.0%	83%	73%	67%	83%	82%	68%
74.7%	86%	75%	72%	72%	71%	72%
76.3%	79%	78%	74%	79%	74%	74%
62.0%	63%	64%	71%	55%	71%	48%
53.8%	61%	59%	26%	58%	56%	63%
66.7%	68%	68%	64%	68%	64%	68%
56.0%	62%	49%	63%	63%	50%	49%
58.5%	61%	63%	58%	56%	59%	54%
39.0%	44%	43%	30%	47%	24%	46%
72.5%	72%	77%	67%	73%	69%	77%
45.7%	43%	56%	36%	45%	47%	47%
65.0%	69%	71%	71%	59%	54%	66%
79.7%	79%	82%	81%	75%	73%	88%
49.8%	43%	44%	53%	54%	47%	58%
62.0%	65%	52%	56%	65%	66%	68%
58.7%	58%	59%	48%	66%	59%	62%
60.0%	56%	81%	55%	59%	61%	48%
71.3%	71%	72%	63%	74%	75%	73%
67.0%	66%	100%	20%	72%	100%	44%
43.7%	37%	49%	41%	38%	41%	56%
58.7%	64%	55%	59%	58%	60%	56%
78.5%	77%	83%	85%	73%	72%	81%
81.0%	85%	85%	75%	85%	71%	85%
46.2%	49%	52%	47%	44%	41%	44%
55.2%	58%	56%	56%	57%	50%	54%
57.3%	58%	53%	56%	61%	58%	58%
64.0%	53%	67%	72%	66%	61%	65%
67.8%	75%	75%	62%	70%	59%	66%
45.3%	54%	52%	30%	51%	49%	36%
68.0%	73%	52%	52%	78%	78%	75%
63.7%	63%	51%	59%	69%	69%	71%
57.0%	63%	65%	54%	63%	37%	60%
50.2%	54%	56%	32%	53%	55%	51%
64.0%	58%	57%	78%	68%	57%	66%
51.2%	56%	69%	37%	56%	48%	41%
70.8%	60%	78%	77%	74%	62%	74%
55.2%	52%	59%	58%	55%	53%	54%
81.0%	79%	71%	79%	90%	83%	84%
66.5%	66%	64%	75%	71%	54%	69%
55.2%	59%	70%	34%	50%	59%	59%
74.5%	80%	76%	81%	69%	69%	72%
72.0%	78%	73%	60%	76%	71%	74%
58.3%	57%	56%	62%	57%	60%	58%
68.8%	70%	73%	62%	71%	61%	76%
58.8%	69%	66%	33%	70%	48%	67%
73.8%	78%	71%	73%	79%	71%	71%
63.2%	75%	74%	51%	58%	71%	50%
67.8%	65%	64%	74%	67%	64%	73%
50.0%	50%	48%	41%	55%	58%	48%
49.8%	55%	63%	31%	38%	64%	48%
61.8%	63%	61%	63%	60%	60%	64%
74.2%	78%	75%	61%	82%	67%	82%
68.3%	60%	69%	75%	73%	60%	73%
70.0%	65%	80%	71%	61%	80%	63%
66.5%	64%	68%	74%	61%	64%	68%
70.7%	69%	70%	79%	68%	66%	72%
75.5%	75%	79%	75%	75%	70%	79%
61.8%	64%	54%	76%	62%	55%	60%
70.8%	65%	48%	89%	65%	68%	90%
74.3%	78%	81%	81%	73%	60%	73%
48.2%	45%	56%	41%	51%	41%	55%
52.5%	52%	58%	38%	62%	62%	43%
46.5%	50%	52%	32%	51%	39%	55%
44.5%	42%	54%	45%	41%	24%	61%
69.3%	69%	60%	71%	70%	76%	70%
75.2%	74%	73%	62%	83%	86%	73%
85.0%	75%	80%	87%	90%	89%	89%
71.0%	73%	65%	54%	72%	85%	77%
53.5%	76%	81%	10%	64%	38%	52%
56.0%	65%	100%	44%	51%	38%	38%
50.8%	56%	66%	40%	46%	49%	48%
33.2%	32%	48%	22%	30%	32%	35%
52.2%	54%	49%	52%	55%	49%	54%
71.3%	69%	74%	63%	76%	67%	79%
55.0%	60%	60%	45%	54%	58%	53%
66.3%	70%	68%	68%	56%	66%	70%
67.3%	74%	67%	67%	69%	56%	71%
85.0%	92%	80%	92%	80%	84%	82%
78.5%	81%	71%	76%	77%	84%	82%
68.2%	79%	80%	68%	63%	53%	66%