	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 87.6%	4th 84.3%	19th 77.1%	16th 78.1%	6th 83.3%	18th 77.7%	10th 81.5%	8th 83.0%	11th 81.5%	5th 83.8%	9th 81.6%	15th 78.3%	7th 83.3%	13th 79.1%	2nd 85.2%	3rd 84.5%	14th 78.9%	21st 75.9%	12th 80.8%	20th 76.9%	17th 77.9%
85.5%	95%	92%	80%	89%	89%	67%	84%	89%	88%	88%	86%	76%	91%	78%	89%	91%	88%	76%	88%	86%	85%
86.5%	85%	76%	93%	93%	90%	87%	90%	85%	79%	92%	84%	88%	92%	92%	93%	89%	77%	72%	90%	83%	86%
62.5%		69%	0%	0%	62%	77%	62%	73%	62%	77%	72%	74%	77%	75%	70%	72%	69%	70%	66%	52%	72%
91.9%	95%	85%	97%	92%	95%	88%	94%	95%	95%	92%	93%	92%	96%	87%	97%	96%	82%	85%	92%	89%	92%
88.9%	94%	91%	88%	88%	78%	96%	86%	98%	92%	97%	97%	92%	94%	96%	92%	96%	87%	80%	81%	64%	80%
87.2%	90%	95%	89%	95%	91%	90%	86%	93%	91%	86%	86%	91%	87%	76%	85%	88%	82%	94%	89%	82%	66%
87.3%	86%	82%	86%	87%	77%	93%	85%	90%	90%	88%	86%	91%	87%	95%	87%	92%	92%	88%	86%	93%	72%
78.5%	86%	79%	74%	76%	74%	50%	81%	90%	82%	76%	80%	76%	82%	74%	93%	84%	83%	83%	67%	82%	77%
84.0%	85%	88%	80%	88%	76%	63%	76%	78%	83%	92%	88%	89%	89%	93%	92%	97%	94%	80%	81%	76%	76%
90.4%	95%	87%	92%	94%	92%	98%	85%	85%	92%	93%	92%	92%	91%	92%	91%	89%	80%	78%	92%	92%	96%
81.8%	87%	90%	92%	92%	86%	91%	89%	87%	85%	76%	85%	88%	66%	66%	81%	81%	68%	56%	84%	86%	81%
83.4%	96%	87%	90%	94%	92%	87%	85%	90%	87%	76%	75%	93%	71%	83%	85%	71%	80%	44%	88%	94%	84%
82.6%	85%	86%	82%	88%	89%	88%	81%	80%	86%	89%	95%	77%	90%	91%	79%	84%	70%	70%	84%	70%	70%
87.5%	87%	86%	87%	90%	84%	77%	91%	95%	88%	94%	91%	75%	88%	80%	91%	92%	84%	92%	93%	95%	78%
85.6%	88%	87%	91%	84%	86%	84%	91%	86%	86%	87%	90%	79%	86%	86%	87%	89%	85%	75%	83%	83%	85%
85.7%	96%	90%	97%	94%	91%	64%	81%	92%	86%	89%	79%	81%	89%	83%	90%	88%	87%	81%	84%	83%	74%
65.0%		72%	75%	72%	63%	55%	68%	47%	65%	71%	72%	55%	59%	55%	71%	72%	67%	54%	71%	60%	77%
69.9%	80%	68%	78%	85%	74%	46%	59%	72%	66%	68%	58%	66%	73%	56%	71%	72%	82%	74%	73%	81%	66%
66.9%	72%	56%	69%	61%	81%	50%	68%	74%	68%	85%	63%	32%	76%	59%	85%	84%	74%	57%	54%	71%	65%
85.6%	97%	95%	98%	92%	96%	76%	96%	82%	76%	94%	85%	75%	92%	75%	87%	93%	73%	71%	79%	75%	91%
87.2%	93%	97%	87%	89%	98%	71%	94%	87%	89%	93%	88%	94%	94%	86%	92%	91%	80%	83%	79%	73%	74%
86.5%	86%	90%	85%	84%	91%	83%	92%	91%	90%	90%	81%	91%	94%	90%	92%	91%	87%	66%	81%	90%	72%
79.3%	75%	71%	86%	80%	93%	88%	84%	85%	68%	87%	84%	62%	81%	88%	76%	73%	75%	79%	84%	72%	75%
85.6%	95%	94%	92%	93%	95%	93%	82%	84%	87%	89%	89%	76%	88%	83%	91%	87%	74%	74%	83%	74%	74%
85.5%	87%	89%	85%	91%	88%	86%	90%	85%	87%	93%	79%	75%	89%	80%	86%	90%	91%	91%	92%	76%	66%
77.1%	78%	82%	82%	84%	86%	78%	75%	77%	79%	82%	82%	76%	80%	80%	75%	81%	62%	66%	81%	58%	76%
76.8%	88%	79%	77%	83%	80%	60%	72%	82%	77%	78%	57%	75%	82%	62%	82%	80%	80%	79%	80%		83%
79.4%	83%	90%	75%	73%	85%	60%	77%	95%	85%	78%	75%	70%	77%	63%	95%	87%	83%	82%	71%		84%
74.3%	87%	88%	87%	91%	83%	65%	77%	71%	67%	67%	72%	75%	65%	63%	82%	78%	66%	62%	67%	67%	80%
76.2%	80%	83%	81%	90%	89%	80%	65%	82%	79%	74%	76%	63%	77%	70%	82%	71%	81%	67%	79%	66%	65%
84.8%	92%	84%	87%	88%	84%	85%	83%	84%	83%	86%	87%	87%	84%	87%	89%	89%	79%	84%	83%	70%	85%
78.0%		89%	0%	0%	96%	80%	96%	84%	96%	80%	85%	83%	80%	82%	87%	85%	89%	87%	92%	87%	82%
59.7%		64%	0%	0%	57%	72%	57%	68%	57%	72%	67%	69%	72%	69%	65%	66%	63%	65%	60%	94%	57%
80.0%	85%	78%	81%	90%	92%	74%	75%	78%	82%	81%	76%	74%	77%	74%	83%	81%	81%	84%	73%	79%	82%
72.4%	83%	85%	74%	80%	49%	73%	67%	67%	64%	62%	65%	68%	70%	68%	75%	70%	75%	70%	94%		90%
84.4%	89%	84%	95%	90%	74%	87%	90%	91%	84%	87%	81%	80%	90%	79%	81%	89%	79%	77%	81%	80%	85%
85.1%	89%	83%	88%	85%	87%	90%	89%	80%	85%	84%	90%	87%	90%	87%	91%	90%	89%	83%	83%	63%	75%
85.3%	88%	93%	92%	92%	84%	96%	87%	95%	91%	90%	93%	81%	97%	85%	95%	98%	74%	68%	93%	50%	50%
82.3%	95%	88%	89%	89%	85%	71%	86%	88%	89%	91%	86%	79%	86%	75%	91%	87%	71%	74%	69%	67%	72%
81.9%		90%	0%	0%	83%	99%	83%	94%	83%	99%	93%	95%	98%	96%	91%	93%	89%	91%	86%	79%	96%
83.2%	87%	89%	81%	87%	94%	77%	87%	87%	91%	80%	82%	70%	80%	78%	87%	79%	65%	89%	80%	88%	89%
80.0%	83%	82%	78%	79%	82%	68%	82%	82%	75%	86%	75%	78%	78%	83%	83%	82%	78%	81%	83%	73%	89%
74.9%		90%	75%	65%	63%	80%	76%	52%	68%	65%	90%	78%	77%	80%	77%	76%	76%	83%	76%	74%	77%

Model Similarity Dendrogram

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