	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	1st 84.7%	2nd 83.7%	16th 77.9%	18th 77.2%	7th 82.6%	19th 77.1%	11th 81.6%	9th 82.0%	8th 82.3%	6th 83.0%	10th 81.9%	15th 78.9%	4th 83.4%	17th 77.4%	5th 83.4%	3rd 83.4%	20th 76.7%	21st 75.5%	12th 80.0%	14th 80.0%	13th 80.0%
85.7%	90%	88%	90%	87%	85%	71%	80%	87%	86%	87%	89%	90%	86%	82%	84%	92%	77%	85%	86%	89%	88%
85.9%	87%	91%	91%	86%	64%	95%	89%	91%	89%	88%	89%	82%	94%	83%	82%	91%	80%	83%	93%	79%	77%
62.4%	71%	65%	0%	0%	58%	73%	68%	71%	62%	73%	73%	70%	70%	71%	60%	64%	62%	75%	65%	91%	69%
91.7%	95%	86%	95%	92%	93%	85%	93%	93%	97%	94%	95%	90%	97%	89%	95%	95%	85%	84%	89%	88%	96%
89.1%	98%	88%	90%	88%	85%	93%	92%	93%	89%	87%	98%	95%	89%	89%	94%	87%	91%	71%	88%	90%	76%
79.3%	85%	87%	83%	87%	85%	75%	79%	87%	76%	77%	83%	73%	81%	73%	71%	73%	72%	83%	76%	80%	80%
87.2%	88%	84%	87%	85%	81%	91%	80%	92%	92%	90%	89%	95%	89%	94%	92%	83%	72%	83%	80%	91%	93%
77.1%	86%	78%	72%	84%	74%	49%	79%	88%	81%	78%	72%	75%	82%	72%	83%	85%	82%	78%	65%	85%	72%
86.3%	82%	91%	90%	88%	88%	70%	80%	77%	88%	96%	90%	91%	95%	90%	88%	96%	84%	89%	87%	76%	76%
86.3%	89%	90%	86%	91%	90%	90%	77%	72%	82%	80%	94%	90%	90%	90%	87%	82%	75%	79%	90%	94%	94%
87.3%	84%	83%	92%	93%	89%	94%	93%	87%	89%	77%	93%	99%	77%	80%	82%	88%	88%	75%	87%	93%	91%
87.3%	91%	90%	96%	98%	96%	83%	90%	89%	89%	82%	86%	94%	79%	81%	90%	90%	78%	66%	93%	79%	93%
80.7%	75%	85%	80%	85%	87%	90%	80%	79%	78%	85%	88%	78%	88%	88%	84%	81%	70%	71%	82%	69%	71%
86.1%	95%	89%	92%	97%	94%	71%	94%	88%	95%	93%	80%	68%	96%	69%	87%	94%	79%	79%	90%	75%	84%
86.5%	88%	91%	93%	88%	87%	87%	90%	87%	89%	82%	90%	82%	92%	85%	82%	86%	86%	72%	84%	87%	89%
85.8%	93%	91%	88%	88%	87%	76%	84%	91%	91%	87%	83%	78%	90%	75%	95%	87%	82%	92%	85%	84%	75%
61.2%	68%	70%	71%	59%	68%	58%	67%	46%	55%	61%	58%	54%	51%	54%	65%	70%	68%	48%	69%	61%	65%
74.7%	90%	73%	88%	86%	90%	50%	67%	82%	74%	76%	62%	73%	82%	61%	78%	77%	76%	73%	73%	68%	70%
69.5%	67%	56%	79%	63%	63%	52%	72%	80%	78%	90%	67%	51%	85%	63%	88%	86%	73%	59%	52%	67%	68%
85.2%	96%	96%	90%	95%	89%	77%	96%	79%	79%	94%	80%	81%	86%	79%	87%	87%	78%	71%	86%	79%	85%
86.8%	81%	93%	91%	87%	94%	78%	94%	83%	95%	89%	92%	91%	95%	80%	88%	95%	77%	82%	77%	74%	86%
86.1%	88%	90%	87%	82%	91%	74%	90%	90%	92%	89%	84%	90%	90%	88%	87%	89%	86%	80%	77%	89%	75%
77.6%	78%	65%	85%	74%	91%	88%	88%	85%	68%	88%	81%	76%	73%	92%	69%	74%	65%	63%	81%	84%	61%
85.5%	87%	89%	90%	89%	80%	91%	83%	85%	84%	89%	90%	76%	87%	92%	86%	84%	77%	76%	83%	86%	91%
83.8%	80%	88%	90%	92%	84%	78%	92%	86%	92%	88%	92%	72%	87%	68%	82%	86%	92%	75%	88%	68%	79%
75.4%	72%	77%	77%	79%	78%	75%	73%	66%	77%	78%	82%	74%	75%	84%	74%	71%	65%	71%	81%	78%	77%
76.6%	84%	77%	80%	84%	82%	64%	71%	83%	78%	79%	60%	73%	80%	64%	80%	80%	74%	82%	78%	77%	79%
79.5%	83%	86%	75%	80%	96%	62%	77%	90%	87%	73%	77%	71%	79%	64%	90%	99%	78%	75%	63%	88%	76%
69.3%	82%	88%	83%	86%	81%	57%	68%	61%	70%	65%	57%	77%	65%	56%	71%	68%	57%	56%	65%	74%	69%
77.0%	78%	85%	80%	84%	82%	68%	63%	78%	80%	77%	79%	64%	84%	72%	92%	78%	64%	76%	79%	90%	63%
84.3%	88%	79%	88%	87%	86%	86%	81%	81%	84%	88%	86%	81%	85%	85%	88%	84%	84%	84%	83%	79%	83%
71.8%	76%	82%	0%	0%	89%	73%	78%	76%	84%	73%	73%	76%	76%	76%	85%	82%	85%	85%	81%	80%	78%
55.1%	65%	59%	0%	0%	53%	67%	62%	65%	57%	67%	67%	64%	64%	65%	58%	58%	56%	53%	59%	56%	63%
82.4%	92%	84%	84%	94%	82%	77%	80%	82%	83%	87%	80%	77%	78%	77%	86%	84%	82%	83%	76%	78%	85%
77.0%	88%	89%	80%	81%	75%	80%	63%	69%	64%	67%	67%	64%	70%	71%	79%	77%	80%	83%	95%	89%	85%
84.9%	90%	90%	94%	91%	74%	84%	91%	91%	86%	90%	87%	78%	90%	76%	88%	88%	84%	67%	78%	77%	89%
87.5%	87%	92%	88%	84%	79%	89%	92%	83%	88%	87%	91%	93%	91%	83%	89%	90%	89%	77%	85%	90%	90%
84.9%	90%	88%	97%	88%	85%	99%	89%	92%	88%	97%	92%	75%	93%	69%	87%	89%	73%	58%	91%	48%	94%
81.5%	98%	85%	87%	84%	86%	70%	81%	92%	87%	86%	79%	74%	87%	64%	95%	85%	80%	71%	62%	81%	77%
86.9%	98%	95%	0%	0%	88%	96%	99%	99%	93%	96%	96%	99%	99%	98%	99%	95%	92%	94%	96%	92%	100%
81.6%	84%	85%	83%	80%	95%	77%	81%	85%	97%	81%	86%	75%	78%	77%	83%	81%	56%	82%	84%	89%	74%
79.3%	82%	86%	78%	78%	75%	71%	84%	82%	77%	87%	75%	84%		80%	82%	80%	78%	69%	83%	78%	77%
75.8%	71%	77%	78%	77%	72%	81%	78%	63%	69%	69%	89%	81%	77%	79%	73%	77%	68%	90%	77%	69%	76%

Model Similarity Dendrogram

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