	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
Score	2nd 79.8%	10th 77.8%	4th 79.0%	1st 79.8%	6th 78.1%	21st 71.8%	14th 76.8%	7th 78.1%	9th 78.0%	8th 78.0%	12th 77.5%	19th 73.0%	16th 75.3%	20th 73.0%	5th 78.8%	3rd 79.1%	17th 74.8%	15th 75.6%	18th 74.1%	11th 77.7%	13th 77.5%
77.0%	78%	74%	81%	81%	80%	75%	82%	78%	81%	68%	75%	86%	75%	76%	75%	75%	78%	68%	79%	75%	77%
75.0%	68%	82%	79%	77%	60%	75%	85%	69%	73%	78%	77%	73%	78%	72%	75%	73%	71%	77%	82%	76%
64.0%		75%	75%	60%	60%	60%	60%	60%	60%	70%	60%	60%	60%	60%	70%	70%	60%	70%	60%	60%	70%
79.8%	88%	72%	86%	82%	87%	70%	86%	85%	91%	84%	76%	75%	75%	72%	81%	86%	79%	72%	75%	75%	78%
89.5%		86%	86%	91%	91%	84%	95%	96%	94%	94%	84%	84%	84%	84%	95%	95%	89%	93%	84%	84%	96%
84.8%		88%	83%	86%	87%	88%	86%	85%	90%	83%	88%	86%	83%	89%	88%	79%	75%	83%	81%	84%	84%
73.6%	77%	77%	70%	76%	70%	65%	70%	71%	71%	65%	68%	76%	75%	70%	82%	80%	76%	86%	71%	76%	73%
70.0%	78%	70%	69%	74%	75%	61%	67%	78%	67%	70%	69%	66%	66%	57%	76%	80%	71%	70%	69%	70%	66%
62.7%	55%	60%	68%	63%	74%	76%	68%	69%	80%	65%	65%	50%	59%	54%	50%	54%	55%	58%	65%	71%	57%
76.4%	75%	85%	79%	85%	75%	75%	66%	63%	66%	79%	85%	85%	75%	85%	79%	79%	70%	67%	75%		80%
62.1%		70%	83%	72%	75%	62%	65%	66%	58%	69%	63%	55%	61%	38%	61%	61%	35%	38%	72%	73%	65%
87.5%	81%	81%	91%	86%	85%	82%	91%	93%	93%	94%	88%	85%	80%	91%	88%	91%	96%	80%	85%	93%	83%
86.5%	93%	91%	80%	86%	82%	73%	87%	90%	93%	85%	93%	93%	75%	93%	83%	89%	75%	82%	93%	93%	87%
76.0%	80%	72%	76%	81%	80%	81%	73%	77%	78%	80%	80%	66%	79%	80%	71%	73%	69%	65%	80%	80%	74%
82.9%	84%	87%	81%	89%	85%	74%	77%	89%	89%	84%	83%	85%	85%	78%	76%	84%	82%	83%	78%	84%	84%
77.3%	78%	79%	81%	83%	79%	76%	75%	76%	79%	76%	75%	75%	78%	75%	79%	77%	79%	72%	77%	75%	79%
81.1%		87%	91%	91%	75%	79%	87%	64%	72%	83%	83%	82%	72%	78%	91%	89%	74%	88%	75%	80%	81%
75.8%	80%	66%	76%	78%	75%	78%	71%	77%	70%	72%	74%	67%	72%	70%	78%	78%	87%	83%	75%	87%	77%
57.7%	60%	47%	57%	51%	75%	42%	61%	54%	64%	70%	46%	43%	59%	63%	70%	65%	71%	48%	43%	57%	66%
76.8%	90%	77%	81%	81%	78%	67%	85%	92%	86%	79%	55%	55%	79%	73%	72%	77%	78%	83%	78%	73%	73%
85.2%	85%	82%	82%	89%	91%	87%	79%	88%	85%	84%	89%	78%	96%	80%	94%	91%	75%	87%	79%	77%	91%
78.9%	86%	77%	85%	84%	78%	78%	86%	78%	79%	82%	78%	78%	76%	81%	75%	78%	76%	74%	79%	72%	76%
75.0%	68%	68%	72%	70%	82%	81%	89%	84%	83%	85%	80%	55%	76%	83%	70%	72%	58%	72%	86%	73%	69%
90.4%	92%	93%	88%	90%	93%	88%	91%	82%	91%	87%	93%	93%	93%	93%	91%	87%	89%	86%	93%	93%	93%
82.7%	84%	85%	75%	81%	83%	84%	83%	80%	85%	86%	83%	80%	85%	80%	86%	85%	83%	86%	82%		78%
69.2%		76%	72%	75%	71%	55%	82%	67%	73%	70%	82%	68%	66%	59%	75%	69%	57%	63%	70%	73%	61%
73.1%	81%	60%	79%	77%	74%	80%	73%	77%	71%	72%	58%	61%	71%	73%	70%	70%	87%	77%	68%	78%	79%
76.2%	79%	82%	75%	75%	76%	69%	82%	82%	76%	82%	74%	60%	77%	68%	81%	82%	81%	79%	65%	76%	80%
69.2%	71%	93%	83%	81%	71%	66%	73%	69%	68%	58%	55%	55%	55%	60%	74%	77%	63%	70%	69%	70%	73%
78.2%	84%	81%	74%	91%	79%	79%	79%	81%	69%	75%	77%	76%	77%	76%	84%	78%	75%	84%	74%	69%	80%
82.5%	84%	84%	84%	85%	80%	75%	84%	80%	79%	82%	81%	81%	83%	81%	85%	87%	76%	89%	85%	86%	82%
82.5%		77%	84%	83%	100%	65%	65%	88%	93%	77%	100%	100%	77%	65%	77%	77%	79%	100%	65%	100%	77%
67.8%		65%	65%	65%	65%	65%	65%	65%	65%	76%	65%	65%	65%	65%	76%	76%	76%	65%	65%	65%	76%
74.1%	86%	71%	71%	79%	82%	71%	66%	79%	79%	73%	70%	67%	78%	69%	83%	83%	72%	74%	58%	73%	73%
75.0%	84%	88%	92%	87%	43%	66%	62%	78%	69%	60%	71%	66%	66%	79%	84%	90%	80%	82%	82%	65%	82%
76.6%	92%	86%	88%	86%	63%	60%	77%	94%	82%	87%	89%	48%	79%	59%	81%	84%	71%	64%	69%	69%	80%
76.3%	75%	76%	73%	78%	78%	69%	68%	73%	73%	78%	81%	81%	78%	81%	82%	77%	77%	70%	73%	83%	78%
86.9%	91%	97%	91%	85%	71%	84%	87%	85%	85%	93%	89%	84%	84%	84%	90%	88%	95%	81%	84%	84%	92%
79.9%	77%	83%	86%	79%	80%	74%	78%	86%	76%	90%	90%	81%	84%	70%	84%	83%	79%	74%	73%	74%	77%
82.5%		77%	84%	83%	100%	65%	65%	88%	93%	77%	100%	100%	77%	65%	77%	77%	79%	100%	65%	100%	77%
64.0%	70%	57%	67%	72%	82%	39%	66%	62%	70%	73%	89%	56%	66%	45%	62%	70%	48%	63%	48%	77%	62%
75.9%	78%	80%	70%	76%	82%	57%	76%	75%	66%	77%	77%	77%	75%	83%	84%	82%	82%	66%	67%	79%	84%
84.4%		81%	86%	87%	88%	88%	90%	85%	90%	84%	74%	83%	83%	81%	83%	83%	87%	80%	90%	83%	83%

Model Similarity Dendrogram

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