	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 4.1 Fast
Score	4th 84.3%	12th 81.3%	5th 83.9%	1st 84.9%	17th 80.5%	19th 78.3%	10th 81.8%	7th 83.1%	8th 83.0%	6th 83.6%	15th 80.8%	21st 77.7%	9th 82.4%	20th 77.8%	3rd 84.3%	2nd 84.3%	16th 80.7%	18th 78.5%	14th 81.0%	11th 81.8%	13th 81.2%
84.1%	88%	84%	88%	88%	91%	87%	89%	84%	88%	80%	82%	77%	80%	80%	83%	84%	86%	74%	90%	83%	81%
77.5%	75%	77%	81%	79%	70%	81%	84%	80%	75%	81%	85%	68%	78%	74%	82%	70%	80%	73%	80%	75%	80%
76.4%	80%	80%	71%	71%	83%	83%	80%	75%	61%	80%	71%	83%	79%	61%	80%	80%	80%	61%	83%	83%	80%
84.2%	89%	78%	89%	89%	90%	85%	88%	79%	86%	86%	85%	88%	83%	72%	85%	74%	84%	75%	88%	89%	87%
82.8%	81%	79%	80%	89%	79%	79%	84%	86%	83%	89%	79%	79%	85%	79%	92%	98%	85%	79%	79%	79%	76%
87.3%	95%	94%	96%	95%	90%	86%	81%	88%	92%	82%	77%	76%	80%	79%	87%	91%	89%	88%	89%	89%	89%
86.3%	89%	85%	84%	86%	84%	82%	82%	88%	88%	84%	83%	86%	84%	79%	88%	92%	92%	95%	87%	84%	90%
79.9%	84%	71%	76%	80%	79%	72%	71%	87%	74%	80%	78%	87%	79%	78%	88%	87%	78%	83%	79%	83%	83%
86.0%	79%	85%	84%	85%	96%	78%	91%	98%	96%	81%	91%	84%	87%	81%	83%	79%	92%	73%	87%	91%	86%
85.1%	88%	80%	86%	91%	88%	88%	87%	82%	83%	90%	86%	80%	88%	80%	85%	86%	84%	76%	88%	88%	83%
77.0%	83%	84%	86%	86%	82%	83%	73%	87%	72%	73%	77%	86%	68%	66%	73%	82%	57%	46%	85%	79%	88%
84.0%	84%	84%	91%	87%	87%	89%	82%	82%	89%	83%	87%	80%	85%	86%	87%	88%	82%	74%	82%	75%	80%
82.0%	80%	81%	79%	81%	77%	86%	84%	86%	84%	82%	79%	79%	86%	79%	82%	87%	82%	85%	79%	85%	79%
88.5%	92%	90%	88%	89%	89%	79%	90%	93%	90%	90%	90%	77%	91%	91%	92%	91%	88%	85%	89%	91%	84%
85.3%	87%	85%	82%	86%	79%	91%	85%	88%	88%	86%	88%	85%	86%	78%	84%	82%	88%	90%	86%	85%	83%
83.9%	90%	78%	86%	83%	87%	81%	79%	84%	87%	82%	85%	69%	85%	85%	82%	82%	87%	91%	87%	85%	86%
59.7%	64%	64%	65%	66%	54%	59%	54%	37%	59%	67%	59%	59%	44%	51%	70%	62%	66%	62%	56%	69%	66%
78.0%	82%	69%	82%	81%	85%	78%	75%	73%	78%	79%	74%	65%	78%	66%	84%	76%	77%	91%	75%	84%	86%
77.8%	82%	70%	92%	76%	46%	62%	85%	85%	84%	87%	72%	57%	86%	74%	86%	88%	74%	87%	70%	88%	83%
89.6%	94%	83%	91%	87%	82%	85%	91%	95%	94%	91%	83%	90%	93%	90%	86%	90%	94%	90%	93%		90%
88.4%	90%	88%	87%	93%	92%	90%	87%	90%	90%	90%	91%	87%	90%	90%	90%	87%	84%	86%	84%	86%	85%
88.5%	90%	91%	81%	86%	88%	87%	87%	96%	89%	84%	87%	87%	91%	90%	89%	90%	92%	79%	93%	94%	88%
73.2%	73%	69%	76%	75%	57%	74%	82%	79%	73%	77%	75%	64%	75%	77%	72%	72%	74%	74%	75%	71%	73%
80.8%	85%	78%	87%	80%	86%	81%	83%	81%	82%	83%	80%	79%	81%	79%	81%	79%	77%	78%	79%	79%	79%
83.1%	85%	87%	83%	84%	80%	84%	80%	85%	86%	84%	80%	78%	89%	83%	84%	84%	80%	89%	88%	86%	66%
78.9%	81%	82%	81%	84%	84%	77%	79%	73%	80%	83%	81%	77%	75%	78%	86%	81%	74%	70%	83%	66%	81%
87.4%	94%	79%	94%	94%	89%	88%	87%	95%	94%	86%	78%	78%	98%	78%	91%	95%	84%	76%	91%	84%	82%
86.3%	85%	87%	89%	86%	90%	77%	90%	89%	88%	90%	86%	84%	88%	77%	93%	88%	85%	96%	76%	84%	85%
69.5%	76%	86%	83%	80%	70%	10%	74%	67%	72%	70%	64%	64%	65%	63%	75%	80%	68%	72%	79%	72%	69%
78.2%	85%	76%	77%	87%	86%	67%	75%	89%	81%	76%	79%	71%	79%	71%	77%	79%	74%	81%	69%	75%	88%
85.7%	88%	91%	85%	90%	85%	88%	86%	83%	88%	84%	84%	84%	85%	78%	91%	84%	85%	82%	90%	84%	84%
67.2%	66%	66%	69%	69%	69%	58%	69%	69%	77%	66%	68%	76%	66%	58%	66%	66%	66%	65%	59%	77%	66%
72.9%	76%	76%	68%	77%	80%	80%	58%	70%	58%	76%	80%	80%	76%	80%	76%	76%	76%	58%	58%	76%	76%
85.1%	90%	76%	86%	93%	96%	82%	81%	91%	91%	91%	81%	78%	86%	72%	86%	90%	90%	86%	77%	81%	83%
75.3%	84%	83%	75%	81%	47%	72%	67%	71%	73%	65%	67%	92%	83%	85%	82%	93%	73%	71%	87%	69%	62%
82.7%	90%	90%	92%	86%	73%	77%	87%	92%	85%	91%	86%	70%	84%	73%	81%	84%	74%	76%	74%	86%	85%
83.1%	88%	82%	82%	85%	83%	82%	89%	90%	82%	90%	78%	78%	82%	82%	83%	87%	81%	79%	79%	82%	82%
87.3%	87%	89%	92%	92%	84%	79%	97%	87%	93%	98%	92%	79%	90%	79%	92%	88%	72%	83%	79%		94%
89.2%	92%	92%	94%	93%	84%	82%	91%	97%	93%	95%	91%	81%	95%	89%	92%	94%	78%	90%	85%		76%
86.5%	82%	83%	95%	95%	77%	80%	77%	82%	77%	99%	94%	77%	83%	80%	99%	99%	99%	80%	82%	77%	99%
78.0%	81%	72%	82%	90%	79%	66%	78%	81%	88%	80%	82%	55%	78%	70%	87%	82%	75%	76%	63%	94%	78%
85.0%	81%	84%	86%	89%	90%	80%	96%	86%	85%	91%	87%	92%	85%	86%	79%	85%	75%	75%	90%	84%	79%
85.4%	91%	88%	85%	85%	76%	91%	83%	75%	92%	92%	73%	76%	93%	97%	96%	95%	88%	76%	89%	80%	73%

Model Similarity Dendrogram

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