	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 70.7%	1st 71.3%	6th 59.2%	3rd 68.3%	5th 65.0%	4th 66.1%
61.2%	75%	61%	62%	59%	61%	49%
66.5%	66%	64%	69%	66%	59%	75%
73.5%	81%	75%	81%	73%	70%	61%
62.8%	66%	75%	59%	57%	62%	58%
59.0%	76%	43%	54%	63%	37%	81%
66.8%	67%	67%	60%	68%	72%	67%
72.3%	80%	78%	53%	73%	75%	75%
58.5%	74%	100%	40%	39%	56%	42%
55.3%	60%	65%	38%	62%	53%	54%
60.2%	70%	66%	37%	64%	66%	58%
71.7%	75%	78%	53%	74%	75%	75%
80.3%	74%	66%	80%	81%	89%	92%
48.0%	61%	75%	10%	60%	41%	41%
79.8%	79%	82%	74%	82%	80%	82%
80.8%	73%	86%	87%	86%	71%	82%
84.5%	90%	86%	86%	85%	74%	86%
67.0%	73%	79%	54%	75%	63%	58%
74.7%	77%	78%	76%	76%	68%	73%
40.0%	56%	46%	27%	41%	24%	46%
76.7%	89%	78%	62%	77%	86%	68%
78.7%	82%	88%	56%	80%	86%	80%
64.3%	73%	73%	47%	66%	69%	58%
68.8%	63%	74%	76%	54%	92%	54%
63.8%	75%	56%	65%	62%	64%	61%
74.5%	68%	67%	87%	76%	65%	84%
75.0%	81%	86%	64%	74%	71%	74%
84.0%	86%	85%	80%	83%	90%	80%
65.0%	78%	80%	48%	67%	67%	50%
72.7%	81%	80%	53%	84%	72%	66%
37.5%	36%	45%	36%	38%	26%	44%
76.0%	83%	66%	72%	82%	76%	77%
61.0%	65%	56%	48%	69%	53%	75%
64.0%	72%	78%	38%	62%	68%	66%
69.8%	75%	75%	58%	74%	67%	70%
24.7%	21%	37%	18%	30%	16%	26%
87.8%	79%	95%	89%	91%	98%	75%
66.5%	71%	76%	53%	67%	66%	66%
40.7%	38%	46%	33%	41%	48%	38%
85.0%	86%	78%	87%	83%	90%	86%
71.5%	70%	75%	68%	74%	75%	67%
72.3%	75%	58%	71%	77%	81%	72%
61.7%	73%	72%	49%	51%	67%	58%
53.8%	56%	77%	42%	56%	45%	47%
78.5%	78%	82%	75%	78%	78%	80%
74.2%	78%	77%	59%	74%	80%	77%
42.7%	40%	47%	44%	46%	29%	50%
39.0%	46%	44%	28%	55%	17%	44%
49.2%	52%	56%	35%	58%	52%	42%
84.0%	94%	96%	68%	85%	80%	81%
65.8%	67%	69%	68%	72%	47%	72%
78.3%	80%	86%	84%	77%	66%	77%
83.7%	86%	76%	87%	83%	83%	87%
92.7%	93%	92%	89%	97%	90%	95%
57.5%	54%	55%	58%	60%	53%	65%