	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	4th 84.0%	7th 83.0%	13th 81.2%	8th 83.0%	6th 83.6%	18th 78.2%	9th 82.1%	15th 80.2%	12th 81.6%	11th 81.6%	1st 84.7%	17th 79.4%	5th 83.6%	14th 81.1%	2nd 84.7%	3rd 84.1%	16th 79.5%	21st 75.0%	10th 81.6%	19th 75.9%	20th 75.3%
85.5%	95%	84%	75%	84%	90%	70%	88%	88%	84%	83%	87%	81%	92%	80%	97%	78%	90%	85%	82%	91%	91%
79.4%	78%	70%	84%	84%	73%	82%	80%	76%	70%	81%	82%	83%	82%	88%	89%	84%	83%	70%	87%		62%
72.3%	69%	70%	72%	78%	72%	75%	69%	74%	70%	75%	75%	75%	72%	70%	69%	67%	75%	68%	62%	68%	94%
91.7%	98%	89%	98%	92%	94%	89%	92%	95%	92%	92%	90%	92%	92%	87%	95%	96%	88%	86%	88%	91%	90%
88.5%	89%	88%	78%	84%	90%	85%	83%	97%	89%	89%	98%	93%	89%	95%	90%	98%	90%	89%	83%	95%	67%
89.2%	84%	88%	83%	88%	93%	93%	90%	95%	94%	88%	90%	91%	90%	89%	83%	90%	97%	92%	85%	80%
79.3%	80%	77%	77%	84%	84%	73%	78%	82%	79%	75%	87%	81%	82%	85%	76%	72%	74%	85%	82%	80%	73%
85.2%	88%	88%	80%	80%	73%	59%	87%	89%	92%	86%	94%	87%	87%	80%	90%	94%	91%	85%	86%	81%	92%
76.1%	82%	69%	65%	71%	75%	61%	68%	69%	68%	78%	86%	84%	74%	84%	90%	90%	76%	82%	69%	76%	81%
87.4%	92%	92%	87%	90%	91%	92%	83%	77%	89%	91%	91%	95%	90%	92%	88%	81%	78%	71%	93%	85%	88%
77.6%	90%	87%	89%	89%	78%	88%	77%	85%	80%	73%	87%	77%	78%	72%	82%	75%	66%	58%	84%	62%	52%
87.1%	87%	93%	95%	90%	93%	92%	86%	92%	95%	87%	94%	92%	95%	92%	94%	89%	88%	80%	98%	10%	87%
85.1%	88%	93%	80%	90%	92%	92%	88%	81%	88%	91%	94%	68%	93%	88%	96%	92%	81%	69%	88%	85%	51%
83.4%	85%	87%	82%	83%	88%	81%	90%	76%	87%	80%	90%	91%	89%	88%	81%	86%	72%	85%	90%	72%	68%
85.1%	89%	91%	86%	90%	91%	85%	86%	81%	84%	84%	90%	77%	90%	92%	92%	91%	75%	74%	89%	86%	64%
82.0%	92%	79%	82%	91%	95%	69%	79%	79%	78%	80%	84%	81%	81%	71%	92%	87%	84%	76%	85%	79%	79%
68.0%	75%	77%	77%	77%	65%	72%	73%	63%	62%	65%	64%	62%	61%	60%	74%	78%	56%	54%	72%	65%	76%
64.8%	74%	66%	66%	71%	66%	48%	56%	64%	61%	58%	58%	56%	70%	56%	67%	67%	75%	77%	67%	69%	68%
57.3%	64%	52%	79%	65%	57%	45%	63%	57%	58%	57%	58%	44%	59%	45%	82%	74%	53%	49%	39%	53%	50%
85.8%	84%	74%	81%	80%	94%	89%	89%	81%	94%	88%	90%	90%	90%	87%	78%	79%	93%	90%	92%	84%	74%
85.2%	84%	86%	81%	80%	91%	82%	93%	78%	92%	83%	96%	87%	92%	92%	83%	84%	78%	76%	84%	82%	85%
82.3%	80%	85%	76%	76%	87%	84%	89%	75%	83%	84%	89%	77%	88%	91%	83%	92%	88%	75%	82%	85%	60%
84.0%	84%	83%	86%	85%	86%	84%	91%	88%	86%	81%	87%	75%	84%	87%	82%	87%	85%	80%	80%	79%	84%
85.1%	90%	95%	83%	91%	93%	95%	79%	81%	89%	94%	88%	71%	96%	90%	98%	96%	86%	73%	87%	56%	57%
82.1%	87%	82%	81%	84%	91%	77%	87%	74%	84%	77%	94%	82%	85%	86%	84%	89%	76%	78%	91%	68%	68%
76.4%	82%	79%	75%	82%	82%	75%	75%	70%	74%	80%	78%	78%	76%	77%	73%	82%	74%	72%	78%	70%	73%
74.9%	81%	78%	72%	79%	77%	61%	70%	76%	73%	76%	69%	76%	82%	68%	84%	82%	82%	65%	75%	71%	76%
87.7%	91%	96%	85%	91%	96%	73%	90%	93%	90%	89%	87%	83%	89%	72%	94%	95%	82%	81%	80%	90%	94%
78.9%	85%	88%	83%	86%	89%	74%	86%	76%	76%	79%	77%	74%	75%	73%	85%	78%	79%	60%	78%		78%
79.2%	82%	89%	82%	86%	95%	67%	76%	81%	73%	73%	85%	70%	83%	74%	80%	78%	80%	78%	79%	78%	74%
79.9%	84%	80%	77%	76%	83%	82%	81%	75%	80%	84%	86%	77%	81%	84%	85%	86%	80%	65%	86%	87%	58%
79.5%	78%	81%	79%	72%	79%	76%	81%	77%	81%	76%	76%	76%	79%	81%	83%	84%	76%	83%	89%		83%
66.1%	67%	65%	67%	73%	67%	70%	64%	69%	65%	70%	70%	70%	67%	65%	63%	61%	69%	63%	57%	63%	63%
83.7%	90%	86%	83%	88%	88%	76%	89%	91%	92%	87%	89%	86%	77%	75%	90%	90%	78%	76%	75%	72%	80%
76.3%	81%	79%	74%	84%	63%	81%	71%	79%	77%	78%	77%	72%	82%	93%	67%	67%	69%	65%	77%	93%	73%
80.2%	82%	85%	87%	82%	72%	83%	85%	85%	83%	85%	85%	78%	86%	81%	73%	85%	85%	67%	83%	70%	63%
79.8%	88%	75%	81%	82%	87%	86%	84%	67%	84%	81%	86%	77%	84%	80%	82%	86%	82%	62%	91%	72%	59%
87.6%	86%	94%	85%	86%	80%	93%	83%	94%	83%	90%	89%	82%	93%	80%	95%	90%	77%	78%	95%	91%	95%
86.9%	92%	90%	96%	95%	92%	81%	91%	87%	91%	96%	87%	87%	90%	84%	94%	91%	81%	70%	81%	75%	73%
96.0%	94%	98%	96%	89%	96%	93%	98%	94%	98%	93%	93%	93%	96%	98%	100%	99%	93%	100%	94%	100%	100%
82.6%	89%	89%	86%	90%	89%	75%	92%	86%	81%	89%	90%	72%	83%	78%	88%	82%	69%	74%	77%	72%	83%
82.5%	82%	87%	77%	77%	84%	74%	84%	89%	83%	87%	82%	84%	89%	87%	85%	80%	82%	72%	85%	74%	88%
80.8%	70%	84%	82%	72%	73%	80%	86%	62%	75%	75%	92%	88%	81%	89%	84%	86%	81%	86%	84%	78%	89%

Model Similarity Dendrogram

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