	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	1st 85.0%	3rd 84.0%	21st 74.9%	7th 81.7%	13th 79.0%	19th 76.7%	11th 80.1%	10th 80.2%	9th 80.4%	5th 82.5%	6th 81.8%	14th 78.9%	8th 81.5%	18th 76.8%	4th 83.3%	2nd 84.3%	15th 78.6%	20th 74.9%	12th 79.6%	16th 78.5%	17th 77.6%
83.1%		94%	75%	84%	79%	75%	80%	93%	84%	77%	82%	80%	91%	75%	91%	86%	90%	77%	85%	84%	81%
76.1%	75%	77%	81%	89%	61%	80%	67%	66%	57%	80%	88%	83%	80%	77%	82%	77%	85%	55%	75%	80%	83%
67.8%		72%	0%	62%	62%	77%	66%	74%	62%	80%	81%	74%	74%	72%	72%	68%	66%	79%	69%	70%	76%
90.6%	94%	85%	92%	92%	94%	88%	93%	93%	95%	93%	93%	93%	93%	86%	91%	89%	85%	91%	87%	86%	90%
84.0%		84%	83%	83%	77%	77%	82%	80%	82%	84%	84%	98%	84%	80%	88%	91%	82%	85%	83%	85%	87%
84.2%		89%	88%	89%	90%	86%	83%	83%	86%	86%	89%	74%	81%	81%	88%	91%	85%	78%	83%	75%	79%
90.0%	86%	88%	89%	81%	78%	97%	90%	97%	96%	92%	90%	95%	91%	94%	95%	97%	94%	96%	79%	95%	69%
75.1%	78%	76%	70%	69%	60%	48%	80%	87%	88%	80%	80%	76%	82%	68%	93%	80%	80%	68%	66%	79%	70%
75.7%	86%	71%	71%	66%	70%	51%	67%	69%	71%	73%	80%	91%	71%	71%	88%	95%	86%	74%	72%	75%	91%
91.3%	93%	91%	92%	95%	93%	93%	87%	86%	93%	92%	93%	93%	93%	93%	86%	91%	86%	85%	93%	93%	96%
82.1%		88%	89%	90%	78%	88%	88%	82%	87%	79%	90%	89%	80%	80%	75%	83%	65%	57%	82%	84%	87%
81.7%	92%	85%	88%	93%	88%	86%	84%	88%	85%	79%	73%	92%	75%	70%	76%	75%	74%	76%	85%	76%	75%
85.4%	90%	97%	86%	81%	82%	86%	88%	86%	87%	95%	94%	88%	93%	89%	74%	96%	74%	74%	85%	74%	74%
86.7%	87%	92%	81%	88%	70%	77%	91%	88%	93%	94%	89%	78%	90%	81%	90%	94%	85%	96%	95%	92%	70%
87.2%	92%	87%	88%	95%	89%	93%	85%	76%	84%	92%	88%	80%	92%	93%	93%	96%	79%	68%	85%	85%	92%
77.3%	82%	87%	88%	88%	74%	61%	75%	83%	82%	85%	77%	67%	84%	65%	86%	84%	86%	66%	74%	65%	65%
63.4%		83%	69%	67%	68%	68%	63%	52%	65%	65%	66%	69%	54%	50%	64%	77%	59%	42%	65%	58%
64.0%	67%	63%	70%	69%	69%	47%	53%	69%	61%	63%	55%	56%	67%	50%	67%	61%	76%	78%	63%	80%	59%
75.6%	76%	67%	85%	76%	80%	58%	79%	77%	86%	93%	69%	63%	75%	77%	86%	92%	77%	62%	64%		71%
87.7%	84%	93%	92%	87%	83%	84%	97%	87%	85%	89%	86%	87%	90%	83%	77%	94%	86%	84%	98%	85%	91%
84.6%	92%	95%	81%	81%	86%	67%	87%	93%	87%	89%	88%	87%	85%	81%	94%	88%	88%	89%	72%	75%	71%
85.5%	86%	89%	87%	80%	91%	81%	90%	89%	92%	87%	83%	87%	90%	85%	87%	94%	78%	83%	73%	89%	74%
82.8%	89%	88%	78%	78%	91%	87%	90%	84%	77%	90%	90%	82%	82%	75%	75%	81%	78%	82%	85%	78%	78%
84.0%	89%	81%	86%	83%	89%	89%	88%	80%	89%	91%	91%	76%	90%	91%	85%	89%	76%	71%	77%	76%	76%
86.2%	91%	89%	87%	89%	86%	79%	91%	89%	90%	91%	85%	73%	88%	72%	92%	90%	78%	92%	90%	83%	86%
74.5%		73%	76%	76%	78%	68%	70%	70%	75%	79%	73%	80%	76%	75%	77%	84%	69%	69%	76%	76%	71%
68.3%	82%	73%	70%	70%	66%	58%	62%	75%	73%	69%	58%	66%	74%	57%	75%	72%	81%	57%	70%	64%	62%
85.6%	93%	98%	79%	84%	77%	64%	90%	97%	92%	81%	90%	77%	85%	67%	92%	98%	91%	89%	76%	87%	90%
76.0%	80%	93%	87%	92%	86%	70%	77%	73%	76%	69%	70%	72%	67%	62%	86%	74%	72%	67%	74%	71%	77%
67.8%		78%	72%	73%	79%	63%	50%	73%	74%	68%	72%	51%	67%	66%	68%	76%	66%	65%	78%	48%	68%
76.7%	77%	76%	78%	77%	83%	84%	76%	73%	75%	79%	76%	85%	78%	83%	76%	80%	65%	68%	79%	60%	83%
81.4%		85%	0%	95%	95%	80%	91%	83%	95%	77%	76%	83%	83%	85%	86%	90%	91%	78%	88%	81%	86%
61.3%		65%	0%	55%	55%	70%	59%	67%	55%	72%	73%	67%	67%	65%	66%	60%	59%	71%	62%	69%	69%
86.9%	90%	89%	91%	95%	90%	83%	84%	84%	89%	88%	84%	77%	85%	84%	91%	87%	90%	89%	82%	83%	90%
68.0%	70%	74%	76%	71%	45%	76%	59%	62%	56%	58%	65%	63%	69%	58%	80%	60%	63%	83%	86%	79%	75%
82.5%	91%	85%	94%	94%	75%	82%	88%	87%	76%	88%	85%	73%	86%	75%	85%	86%	79%	74%	74%	74%	81%
81.9%	85%	77%	82%	83%	94%	90%	83%	70%	84%	78%	83%	80%	86%	89%	82%	85%	80%	64%	86%	85%	73%
84.4%		90%	89%	87%	82%	85%	85%	84%	83%	90%	90%	77%	91%	83%	94%	96%	77%	77%	91%	89%	49%
87.5%	87%	93%	95%	93%	92%	83%	94%	86%	88%	97%	89%	88%	87%	82%	93%	87%	82%	81%	78%	85%	78%
87.3%		93%	0%	82%	82%	98%	87%	95%	82%	99%	98%	95%	95%	93%	93%	88%	87%	100%	90%	97%	92%
83.5%	89%	88%	94%	88%	90%	80%	91%	91%	84%	87%	88%	74%	88%	78%	87%	88%	80%	25%	89%	85%	90%
76.8%	77%	82%	71%	74%	73%	69%	85%	79%	77%	82%	77%	81%	76%	86%	76%	78%	78%	71%	81%	76%	63%
72.2%		87%	69%	70%	68%	74%	70%	47%	59%	69%	88%	71%	71%	74%	79%	75%	71%	85%	79%	66%	72%

Model Similarity Dendrogram

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