	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 69.0%	4th 66.1%	5th 65.4%	1st 70.2%	6th 64.6%	3rd 68.0%
69.0%	82%	63%	72%	69%	69%	59%
69.5%	71%	65%	68%	75%	63%	75%
78.8%	83%	92%	82%	88%	66%	62%
58.3%	63%	73%	51%	55%	54%	54%
66.2%	76%	46%	64%	68%	67%	76%
72.5%	69%	73%	68%	75%	74%	76%
80.3%	79%	62%	88%	87%	83%	83%
61.8%	69%	100%	50%	42%	59%	51%
55.8%	60%	63%	47%	61%	50%	54%
81.7%	84%	82%	61%	94%	78%	91%
66.0%	71%	73%	48%	63%	68%	73%
44.7%	47%	31%	43%	45%	49%	53%
46.3%	61%	72%	10%	56%	37%	42%
72.5%	66%	77%	78%	78%	61%	75%
49.0%	48%	45%	57%	51%	36%	57%
76.3%	78%	68%	72%	80%	79%	81%
67.2%	69%	65%	67%	67%	74%	61%
69.7%	71%	61%	72%	71%	71%	72%
60.7%	66%	61%	49%	66%	52%	70%
67.5%	67%	58%	78%	74%	55%	73%
67.3%	67%	62%	79%	70%	56%	70%
77.2%	71%	77%	74%	83%	70%	88%
48.2%	54%	55%	48%	41%	55%	36%
60.3%	67%	56%	61%	60%	58%	60%
43.8%	36%	34%	56%	54%	34%	49%
64.0%	67%	64%	81%	71%	40%	61%
91.7%	92%	89%	93%	92%	86%	98%
74.8%	88%	81%	72%	66%	76%	66%
69.3%	72%	74%	63%	75%	65%	67%
61.2%	60%	54%	55%	75%	57%	66%
47.2%	45%	68%	37%	46%	50%	37%
66.0%	66%	50%	58%	66%	88%	68%
83.8%	89%	88%	69%	91%	75%	91%
74.0%	63%	65%	90%	79%	65%	82%
34.5%	28%	34%	29%	36%	42%	38%
75.0%	80%	58%	75%	79%	79%	79%
78.8%	79%	62%	81%	85%	83%	83%
67.0%	66%	63%	65%	71%	73%	64%
74.7%	71%	82%	64%	82%	79%	70%
55.8%	56%	46%	52%	55%	63%	63%
69.0%	72%	67%	69%	72%	68%	66%
69.7%	74%	64%	67%	70%	70%	73%
80.3%	76%	64%	80%	88%	87%	87%
81.3%	92%	88%	88%	88%	66%	66%
87.8%	89%	88%	76%	87%	91%	96%
65.8%	63%	61%	71%	64%	67%	69%
52.3%	62%	52%	44%	60%	33%	63%
64.5%	73%	78%	52%	63%	72%	49%
82.5%	75%	76%	93%	88%	77%	86%
76.2%	85%	81%	74%	81%	55%	81%
64.8%	71%	62%	77%	73%	45%	61%
78.3%	73%	78%	79%	82%	83%	75%
78.3%	69%	71%	84%	84%	90%	72%
50.8%	54%	50%	52%	50%	47%	52%