	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	4th 75.1%	6th 74.7%	1st 76.1%	5th 75.0%	19th 70.3%	16th 71.3%	8th 73.9%	17th 71.2%	14th 72.0%	2nd 75.6%	10th 73.7%	18th 70.7%	7th 74.5%	13th 72.7%	11th 73.5%	3rd 75.1%	20th 69.7%	21st 65.7%	15th 71.6%	12th 73.2%	9th 73.7%
75.0%	71%	75%	75%	86%	78%	63%	79%	70%	70%	75%	79%	70%	75%	82%	75%	75%	55%	65%	76%	91%	91%
71.1%	71%	64%	71%	81%	35%	72%	62%	60%	63%	78%	80%	80%	82%	72%	82%	81%	78%	51%	81%	71%	78%
53.4%	51%	50%	55%	44%	44%	55%	51%	53%	48%	56%	59%	61%	56%	56%	56%	56%	51%	63%	47%		56%
88.4%	90%	81%	90%	80%	81%	80%	100%	90%	90%	100%	100%	81%	100%	80%	90%	100%	94%	78%	90%	81%	81%
76.4%	86%	72%	86%	76%	87%	83%	81%	83%	80%	65%	70%	76%	70%	71%	71%	71%	71%	59%	81%	71%	95%
92.1%	96%	97%	96%	96%	95%	93%	88%	88%	86%	95%	95%	92%	86%	92%	85%	88%	95%	99%	95%	83%	95%
82.3%	80%	84%	79%	83%	85%	85%	88%	89%	85%	85%	80%	82%	85%	82%	78%	85%	63%	82%	85%	82%	82%
72.8%	77%	77%	78%	74%	76%	53%	76%	71%	74%	78%	69%	73%	77%	71%	83%	75%	64%	65%	68%	72%	77%
73.8%	81%	66%	70%	67%	71%	56%	60%	66%	65%	86%	79%	79%	79%	78%	81%	86%	92%	59%	65%	82%	82%
74.4%	81%	71%	67%	73%	81%	81%	73%	61%	81%	79%	81%	81%	81%	81%	67%	70%	64%	56%	81%		78%
78.2%	84%	86%	87%	90%	75%	87%	84%	74%	81%	68%	90%	87%	75%	75%	70%	68%	68%	54%	76%	79%	84%
69.2%	70%	71%	73%	71%	71%	69%	69%	73%	73%	72%	69%	58%	62%	77%	69%	69%	63%	60%	71%	73%	71%
73.7%	72%	77%	85%	84%	77%	76%	72%	64%	72%	81%	76%	69%	68%	79%	77%	73%	68%	68%	75%	66%	68%
80.2%	65%	78%	63%	75%	78%	89%	78%	78%	78%	78%	85%	88%	78%	88%	82%	78%	88%	91%	82%	82%	82%
73.9%	77%	77%	77%	90%	72%	79%	77%	62%	73%	84%	77%	62%	73%	75%	77%	76%	62%	56%	76%		77%
66.2%	67%	70%	72%	72%	69%	61%	67%	67%	65%	70%	62%	65%	70%	53%	73%	70%	68%	41%	70%	71%	67%
57.5%	64%	70%	67%	57%	33%	52%	61%	51%	60%	57%	71%	48%	54%	66%	54%	64%	50%	55%	60%	60%	54%
74.8%	74%	75%	75%	69%	86%	67%	80%	69%	73%	79%	79%	73%	73%	75%	79%	74%	71%	69%	70%	82%	78%
50.6%	57%	42%	51%	42%	66%	45%	51%	51%	58%	51%	40%	33%	51%	43%	62%	66%	63%	58%	41%		41%
86.2%	92%	89%	92%	92%	89%	89%	89%	85%	81%	92%	83%	81%	89%	81%	87%	87%	81%	74%	90%	81%	87%
66.9%	70%	72%	69%	70%	72%	61%	70%	64%	71%	71%	71%	68%	71%	66%	63%	70%	58%	57%	56%	71%	64%
83.0%	96%	91%	89%	77%	96%	61%	89%	88%	91%	79%	61%	81%	91%	70%	89%	74%	88%	88%	66%	91%	88%
74.2%	70%	78%	78%	65%	74%	89%	81%	92%	78%	78%	78%	60%	85%	87%	63%	65%	77%	53%	92%	63%	53%
69.1%	77%	79%	85%	85%	74%	74%	67%	61%	67%	79%	72%	48%	69%	68%	69%	74%	61%	48%	72%	61%	61%
70.1%	69%	63%	63%	69%	63%	73%	63%	75%	69%	63%	56%	79%	69%	79%	79%	79%	79%	65%	71%	69%	77%
66.4%	61%	71%	76%	76%	74%	70%	70%	58%	58%	75%	79%	58%	66%	72%	58%	78%	58%	58%	67%	61%	51%
64.2%	70%	70%	72%	69%	68%	60%	67%	59%	59%	72%	56%	59%	64%	68%	63%	68%	59%	62%	58%	59%	66%
64.9%	66%	66%	60%	68%	73%	49%	71%	71%	61%	67%	67%	58%	67%	58%	68%	69%	65%	58%	56%	77%	67%
61.2%	69%	73%	73%	80%	73%	55%	72%	56%	53%	55%	53%	49%	53%	52%	62%	65%	59%	53%	59%	59%	62%
77.0%	71%	84%	78%	80%	74%	64%	71%	78%	78%	81%	75%	78%	74%	81%	80%	73%	80%	72%	78%	88%	78%
60.8%	64%	61%	65%	69%	61%	55%	63%	61%	60%	67%	61%	60%	61%	58%	65%	59%	47%	52%	55%	72%	61%
82.8%	81%	80%	86%	73%	73%	86%	81%	83%	77%	87%	90%	93%	87%	87%	76%	81%	81%	90%	76%	87%	83%
93.1%	99%	95%	99%	88%	88%	98%	97%	99%	93%	97%	94%	91%	97%	97%	90%	99%	91%	88%	91%	68%	97%
82.8%	87%	83%	87%	87%	52%	82%	80%	92%	86%	82%	79%	81%	81%	85%	87%	87%	86%	88%	76%	81%	90%
70.9%	67%	92%	82%	82%	32%	67%	63%	64%	79%	67%	55%	79%	79%	64%	79%	82%	79%	83%	75%	59%	60%
67.9%	73%	70%	71%	69%	59%	76%	66%	66%	59%	72%	73%	69%	73%	69%	64%	71%	58%	51%	77%	73%	67%
57.9%	62%	56%	66%	66%	59%	65%	60%	52%	62%	62%	62%	55%	62%	53%	59%	62%	46%	46%	52%	56%	52%
76.4%	88%	76%	83%	85%	76%	84%	88%	83%	84%	88%	70%	66%	83%	62%	77%	77%	60%	45%	72%	66%	92%
66.6%	72%	69%	73%	73%	67%	60%	70%	67%	67%	74%	68%	58%	73%	58%	69%	70%	55%	62%	51%	68%	74%
91.4%	91%	89%	95%	83%	83%	96%	91%	93%	87%	97%	100%	97%	97%	97%	83%	93%	97%	95%	85%	85%	85%
68.8%	70%	70%	70%	70%	63%	80%	63%	70%	67%	70%	77%	72%	69%	70%	66%	74%	72%	45%	74%	69%	63%
75.9%	83%	82%	76%	76%	64%	60%	75%	75%	70%	76%	77%	77%	76%	77%	83%	81%	76%	80%	75%	79%	75%
67.4%	66%	72%	66%	64%	56%	67%	72%	50%	64%	64%	72%	67%	73%	73%	72%	66%	56%	81%	66%	67%	81%

Model Similarity Dendrogram

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