	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 72.5%	1st 72.9%	6th 64.6%	3rd 70.7%	5th 67.0%	4th 67.8%
54.7%	67%	48%	57%	57%	52%	47%
62.7%	66%	56%	64%	63%	56%	71%
80.5%	88%	87%	84%	76%	74%	74%
63.8%	58%	81%	66%	58%	64%	56%
71.3%	79%	63%	67%	73%	72%	74%
72.5%	65%	74%	67%	75%	81%	73%
62.5%	71%	66%	45%	66%	62%	65%
60.5%	77%	100%	40%	41%	67%	38%
63.8%	63%	75%	55%	69%	61%	60%
70.3%	74%	75%	60%	76%	72%	65%
77.3%	72%	83%	79%	76%	75%	79%
88.7%	87%	79%	93%	92%	91%	90%
46.3%	61%	75%	10%	53%	41%	38%
70.0%	71%	81%	77%	70%	50%	71%
69.7%	71%	69%	78%	72%	59%	69%
72.2%	83%	64%	70%	74%	61%	81%
56.7%	59%	64%	51%	63%	55%	48%
78.0%	75%	87%	68%	86%	70%	82%
59.0%	71%	63%	47%	62%	49%	62%
80.8%	79%	82%	77%	82%	88%	77%
79.3%	79%	74%	81%	79%	84%	79%
81.5%	94%	82%	66%	83%	88%	76%
52.2%	49%	55%	57%	39%	70%	43%
76.8%	80%	71%	81%	71%	80%	78%
73.5%	75%	86%	84%	72%	52%	72%
78.5%	83%	82%	89%	83%	58%	76%
94.3%	95%	96%	97%	95%	90%	93%
82.0%	92%	88%	65%	90%	85%	72%
64.0%	69%	72%	57%	73%	57%	56%
51.7%	53%	53%	57%	48%	44%	55%
51.0%	50%	66%	33%	50%	66%	41%
64.5%	61%	58%	47%	62%	77%	82%
68.0%	72%	72%	55%	72%	70%	67%
65.8%	67%	71%	57%	69%	65%	66%
41.2%	48%	46%	33%	39%	35%	46%
82.0%	86%	72%	84%	77%	87%	86%
83.0%	88%	84%	71%	86%	87%	82%
48.7%	51%	57%	38%	44%	56%	46%
78.8%	82%	78%	82%	84%	73%	74%
86.0%	85%	83%	84%	90%	88%	86%
85.5%	88%	86%	89%	88%	84%	78%
57.0%	66%	60%	47%	50%	65%	54%
64.7%	65%	81%	56%	76%	54%	56%
70.7%	67%	70%	83%	76%	61%	67%
86.5%	92%	88%	72%	97%	77%	93%
54.3%	49%	52%	56%	63%	49%	57%
41.5%	51%	54%	30%	49%	21%	44%
60.8%	70%	66%	44%	65%	63%	57%
75.3%	83%	90%	57%	71%	82%	69%
72.7%	78%	82%	71%	77%	57%	71%
78.2%	85%	81%	83%	79%	60%	81%
80.0%	78%	79%	77%	79%	89%	78%
88.0%	86%	84%	91%	86%	89%	92%
60.3%	59%	48%	59%	72%	55%	69%