	Claude 3.7 Sonnet	Claude Haiku 4.5	Claude Sonnet 4	Claude Sonnet 4.5	Gemini 2.5 Flash	Gemma 3 12b It	Llama 4 Maverick	Mistral Large 2411	Mistral Medium 3	GPT 4.1	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o	GPT 4o Mini	GPT 5	GPT 5.1	GPT OSS 120b	GPT OSS 20b	Qwen3 30b A3B Instruct 2507	Qwen3 32b	Grok 4.1 Fast
Score	12th 74.3%	6th 75.4%	1st 78.0%	2nd 76.9%	15th 73.0%	13th 73.4%	4th 75.9%	10th 74.6%	7th 75.2%	5th 75.9%	9th 74.7%	20th 71.2%	11th 74.4%	17th 72.6%	8th 74.9%	3rd 76.2%	18th 71.6%	21st 66.7%	14th 73.3%	19th 71.5%	16th 72.7%
75.0%		67%	80%	79%	74%	65%	83%	81%	82%	80%	74%	82%	75%	80%	77%	79%	55%	63%	66%	73%	84%
66.7%		67%	75%	80%	25%	73%	64%	54%	55%	74%	67%	73%	71%	69%	77%	74%	61%	65%	79%	70%	62%
61.0%		61%	76%	55%	55%	67%	63%	65%	57%	65%	71%	59%	55%	63%	55%	61%	62%	59%	57%	57%	57%
80.1%	89%	78%	91%	79%	85%	65%	83%	83%	89%	78%	74%	74%	85%	84%	77%	83%	72%	87%	78%	74%	74%
76.1%		77%	86%	86%	72%	91%	81%	67%	72%	76%	77%	76%	71%	80%	83%	77%	64%	60%	83%	68%	75%
86.7%		87%	82%	88%	88%	90%	90%	93%	93%	88%	93%	80%	88%	93%	75%	82%	84%	91%	87%	86%	75%
81.0%	74%	71%	71%	82%	78%	79%	76%	81%	78%	79%	76%	89%	76%	78%	93%	89%	94%	90%	78%	82%	87%
75.8%		74%	73%	71%	78%	62%	83%	78%	80%	77%	79%	79%	79%	69%	81%	82%	76%		70%	73%	77%
72.7%		77%	74%	74%	84%	72%	80%	74%	84%	75%	71%	70%	71%	67%	60%	58%	71%	74%	74%	60%	84%
73.5%	74%	80%	77%	78%	74%	74%	66%	73%	74%	78%	74%	74%	74%	74%	76%	78%	60%	68%	74%	74%	70%
60.4%		68%	76%	73%	57%	70%	76%	73%	57%	48%	65%	65%	56%	42%	49%	47%	43%	26%	69%	69%	78%
84.8%	72%	88%	95%	86%	86%	84%	89%	87%	89%	88%	89%	78%	80%	81%	90%	86%	88%	76%	82%	89%	78%
70.2%		67%	75%	78%	65%	85%	68%	65%	77%	67%	81%	57%	66%	73%	71%	75%	59%	56%	81%	78%	59%
66.9%	62%	67%	59%	68%	64%	79%	62%	63%	67%	65%	70%	75%	61%	72%	69%	73%	71%	66%	57%	65%	70%
77.8%		74%	82%	78%	82%	81%	82%	80%	80%	74%	86%	73%	78%	75%	77%	78%	65%	79%	77%	74%	81%
74.8%		77%	79%	67%	74%	67%	79%	80%	74%	82%	73%	76%	80%	72%	76%	77%	76%	67%	77%	70%	74%
78.1%		78%	82%	83%	80%	80%	77%	75%	80%	77%	83%	71%	76%	76%	80%	81%	74%	68%	83%		80%
71.9%		70%	77%	80%	85%	48%	66%	77%	74%	70%	58%	79%	76%	64%	81%	76%	90%	61%	51%	76%	79%
58.7%	63%	45%	61%	55%	66%	45%	63%	66%	66%	69%	49%	38%	66%	69%	71%	76%	66%	47%	46%	60%	46%
68.2%	76%	74%	76%	78%	73%	66%	72%	66%	60%	74%	61%	61%	67%	61%	75%	75%	63%	61%	68%	61%	65%
80.1%	85%	89%	87%	78%	84%	89%	74%	76%	86%	95%	86%	75%	83%	94%	69%	78%	75%	59%	81%	70%	70%
72.6%	77%	82%	79%	82%	68%	81%	77%	66%	77%	83%	80%	58%	72%	78%	79%	80%	61%	60%	76%	74%	35%
73.7%	65%	74%	74%	63%	95%	87%	82%	83%	73%	83%	85%	74%	76%	85%	71%	54%	71%	59%	85%	58%	51%
68.0%		78%	76%	75%	64%	76%	56%	62%	67%	74%	76%	44%	68%	65%	69%	73%	67%	64%	77%	64%	64%
73.5%	67%	74%	71%	70%	81%	68%	75%	79%	76%	72%	75%	72%	79%	74%	70%	77%	70%	74%	73%	75%	72%
71.2%		83%	81%	78%	70%	74%	70%	70%	74%	79%	82%	66%	72%	71%	61%	62%	68%	57%	81%		54%
71.7%		71%	79%	77%	76%	52%	83%	81%	71%	76%	56%	82%	71%	62%	72%	74%	75%	60%	63%	67%	87%
78.0%		81%	78%	78%	58%	77%	84%	83%	71%	78%	84%	79%	82%	72%	75%	80%	84%	79%	74%	82%	80%
61.2%	67%	72%	75%	78%	66%	54%	61%	56%	64%	57%	51%	51%	55%	51%	64%	67%	55%	51%	63%	60%	67%
71.3%		77%	69%	76%	83%	71%	63%	75%	77%	65%	73%	65%	65%	72%	82%	70%	87%	47%	77%	62%	69%
69.2%	74%	71%	71%	70%	70%	73%	76%	66%	70%	74%	71%	63%	80%	67%	70%	70%	63%	50%	67%	67%	71%
93.2%		95%	80%	96%	98%	89%	94%	92%	100%	92%	85%	98%	98%	94%	92%	96%	88%	98%	100%	83%	96%
62.1%		61%	76%	55%	55%	67%	63%	65%	57%	65%	71%	59%	55%	63%	55%	61%	69%	59%	57%	53%	77%
74.9%	89%	74%	77%	84%	62%	67%	69%	84%	80%	80%	73%	72%	75%	61%	73%	86%	84%	80%	65%	63%	74%
75.2%	76%	78%	82%	87%	43%	74%	76%	76%	76%	76%	82%	88%	67%	65%	83%	80%	88%	76%	71%	67%	68%
77.5%	76%	79%	91%	77%	60%	89%	93%	76%	71%	77%	75%	78%	80%	78%	65%	81%	71%	70%	82%	84%	75%
61.3%		63%	65%	64%	62%	59%	62%	62%	59%	63%	59%	61%	59%	56%	64%	64%	59%	57%	61%	59%	67%
84.9%		84%	94%	91%	89%	88%	92%	92%	92%	94%	87%	68%	92%	82%	83%	89%	70%	67%	83%	75%	87%
76.5%	80%	81%	83%	79%	79%	76%	79%	79%	81%	78%	79%	71%	81%	69%	84%	81%	67%	66%	61%	76%	77%
94.5%		95%	80%	98%	98%	89%	94%	92%	100%	92%	85%	98%	98%	94%	98%	96%	88%	98%	100%	98%	100%
74.3%		80%	81%	84%	68%	71%	76%	80%	77%	80%	69%	48%	84%	70%	84%	80%	68%	63%	70%	68%	84%
69.1%	72%	76%	64%	64%	71%	53%	71%	59%	66%	59%	74%	66%	67%	75%	76%	77%	68%	77%	67%	77%	72%
85.6%		78%	92%	85%	92%	90%	89%	72%	81%	86%	81%	95%	89%	82%	87%	94%	89%		81%	90%	73%

Model Similarity Dendrogram

Hierarchical clustering of models based on response similarity. Models grouped closer are more similar.