	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 87.0%	12th 83.3%	5th 85.1%	3rd 85.9%	4th 85.6%	19th 80.1%	13th 83.3%	9th 83.7%	7th 84.5%	8th 84.0%	11th 83.4%	21st 79.7%	9th 83.7%	18th 80.3%	2nd 86.3%	6th 84.5%	15th 82.3%	20th 80.0%	17th 80.5%	14th 82.6%	16th 80.7%
84.4%		86%	87%	87%	88%	82%	86%	83%	89%	84%	90%	80%	86%	83%	84%	84%	79%	73%	91%	84%	82%
80.2%	73%	85%	79%	83%	74%	92%	87%	78%	80%	81%	80%	81%	84%	90%	87%	83%	66%	74%	69%	89%	70%
71.1%		74%	63%	74%	74%	54%	75%	67%	63%	75%	74%	80%	74%	74%	75%	75%	75%	74%	54%	74%	75%
86.6%	91%	82%	91%	89%	88%	83%	91%	87%	92%	92%	90%	89%	88%	80%	86%	68%	84%	83%	88%	91%	85%
83.4%		79%	82%	90%	79%	79%	89%	96%	81%	89%	79%	79%	79%	79%	96%	95%	81%	82%	79%		71%
87.0%		95%	91%	94%	98%	90%	89%	91%	89%	78%	82%	90%	82%	83%	86%	86%	81%	80%	83%	82%	90%
85.9%	93%	81%	85%	91%	81%	79%	82%	93%	87%	82%	84%	85%	82%	76%	95%	95%	85%	88%	81%	82%	96%
79.3%	82%	82%	80%	81%	81%	67%	70%	89%	79%	84%	79%	79%	79%	72%	79%	85%	81%	84%	75%	78%	79%
82.3%	80%	71%	75%	79%	92%	70%	81%	87%	82%	87%	85%	92%	81%	75%	83%	80%	90%	82%	87%	88%	81%
87.0%	89%	89%	87%	92%	89%	95%	83%	72%	90%	86%	79%	95%	90%	89%	89%	91%	89%	62%	89%	89%	94%
81.0%		90%	89%	91%	87%	88%	88%	86%	83%	78%	79%	78%	72%	62%	82%	82%	75%	66%	89%	88%	68%
86.3%	92%	92%	87%	95%	94%	81%	76%	95%	92%	78%	85%	94%	89%	89%	92%	80%	79%	71%	89%	88%	75%
90.2%	92%	92%	93%	93%	91%	79%	92%	92%	92%	88%	91%	91%	90%	91%	90%	89%	86%	91%	91%	91%	89%
93.0%	94%	92%	91%	96%	96%	93%	91%	97%	95%	95%	94%	76%	95%	92%	96%	95%	89%	96%	96%	96%	89%
92.2%	94%	93%	93%	93%	93%	96%	93%	95%	89%	93%	93%	93%	92%	94%	86%	89%	91%	88%	93%		93%
92.0%		88%	95%	95%	94%	96%	94%	97%	98%	89%	91%	71%	95%	94%	95%	91%	85%	93%	97%	89%	93%
71.2%		87%	76%	73%	59%	75%	67%	47%	70%	72%	70%	74%	60%	66%	80%	78%	87%	77%	71%	82%	53%
85.9%		79%	87%	88%	89%	92%	85%	90%	90%	82%	85%	62%	88%	90%	92%	86%	89%	90%	89%	88%	77%
64.8%	66%	52%	71%	62%	69%	50%	70%	59%	66%	76%	65%	50%	70%	64%	82%	78%	60%	82%	47%	57%	65%
87.8%	92%	85%	92%	92%	94%	78%	93%	94%	96%	97%	92%	70%	96%	79%	84%	85%	93%	89%	84%	83%	76%
89.9%	92%	85%	95%	95%	97%	89%	92%	88%	92%	97%	88%	88%	95%	89%	89%	93%	85%	84%	86%	79%	90%
91.3%	90%	95%	84%	89%	92%	90%	90%	95%	93%	89%	94%	88%	89%	97%	97%	93%	87%	87%	96%	89%	93%
83.0%	85%	78%	88%	82%	88%	88%	90%	86%	87%	92%	90%	50%	67%	84%	82%	81%	87%	87%	85%	86%	80%
89.7%	91%	80%	93%	98%	93%	95%	96%	91%	86%	92%	90%	91%	92%	91%	87%	84%	92%	85%	93%	88%	76%
91.8%	92%	93%	92%	94%	96%	95%	90%	94%	95%	93%	93%	96%	94%	87%	92%	94%	88%	84%	92%	96%	77%
78.2%		83%	83%	84%	86%	71%	77%	73%	75%	78%	82%	82%	73%	71%	81%	85%	60%	64%	90%	83%	83%
82.7%	90%	70%	90%	87%	84%	85%	82%	89%	79%	82%	67%	72%	88%	92%	88%	77%	91%	83%	66%		91%
78.2%	82%	77%	82%	83%	88%	63%	78%	84%	90%	81%	76%	59%	76%	66%	90%	86%	72%	77%	66%	84%	83%
76.9%	82%	92%	88%	84%	80%	69%	78%	73%	75%	73%	68%	68%	73%	69%	85%	83%	76%	68%	72%	78%	80%
81.3%		79%	83%	85%	93%	78%	82%	86%	85%	77%	79%	87%	79%	75%	83%	70%	79%	79%	78%	88%	81%
93.1%	93%	95%	93%	94%	92%	92%	90%	94%	92%	93%	94%	95%	94%	95%	96%	96%	91%	89%	93%	90%	95%
62.7%		61%	65%	65%	79%	48%	48%	73%	79%	61%	79%	57%	79%	54%	61%	69%	61%	52%	54%	48%	61%
69.1%		68%	70%	68%	68%	93%	93%	60%	61%	68%	68%	73%	68%	68%	68%	68%	68%	68%	48%	68%	68%
82.9%	91%	82%	87%	89%	85%	75%	79%	83%	84%	82%	78%	77%	83%	75%	91%	92%	86%	85%	72%	81%	84%
75.7%	79%	93%	78%	76%	81%	81%	61%	71%	66%	62%	70%	77%	72%	67%	81%	74%	85%	80%	89%	59%	88%
87.2%	89%	94%	88%	85%	86%	82%	89%	90%	88%	89%	89%	84%	97%	81%	84%	88%	84%	85%	79%	93%	87%
91.3%	92%	93%	91%	93%	86%	87%	93%	82%	95%	87%	98%	95%	93%	91%	92%	92%	89%	91%	96%	95%	86%
85.3%		89%	92%	91%	86%	79%	89%	85%	87%	99%	86%	79%	92%	79%	94%	90%	85%	58%	79%	81%	85%
85.6%	92%	87%	93%	92%	89%	80%	91%	91%	84%	92%	89%	76%	93%	76%	85%	84%	85%	78%	79%		77%
83.0%		72%	98%	71%	79%	68%	68%	93%	93%	91%	79%	94%	79%	74%	91%	91%	94%	91%	74%	68%	91%
81.0%	85%	73%	83%	91%	95%	62%	83%	83%	87%	80%	94%	56%	88%	74%	88%	89%	80%	76%	61%	86%	87%
76.2%	74%	77%	75%	79%	81%	65%	81%	77%	76%	84%	74%	82%	75%	82%	78%	71%	73%	73%	82%	72%	70%
83.9%		94%	76%	82%	65%	90%	81%	63%	80%	83%	94%	92%	88%	93%	89%	88%	96%	92%	88%	89%	56%

Model Similarity Dendrogram

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