	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	3rd 86.3%	9th 84.0%	4th 85.6%	1st 86.6%	10th 83.9%	18th 81.3%	21st 80.6%	8th 84.0%	13th 83.4%	6th 84.8%	14th 82.3%	20th 80.6%	7th 84.5%	17th 81.4%	2nd 86.4%	5th 85.2%	15th 82.0%	19th 81.0%	16th 81.5%	11th 83.8%	12th 83.6%
85.0%	82%	85%	92%	87%	85%	84%	86%	85%	90%	85%	87%	77%	85%	87%	89%	83%	83%	88%	81%	87%	78%
81.0%	70%	86%	75%	83%	81%	93%	93%	78%	80%	81%	86%	78%	80%	87%	91%	74%	77%	72%	84%	80%	72%
73.3%	78%	78%	68%	74%	79%	94%	10%	64%	58%	78%	79%	94%	79%	79%	78%	78%	78%	79%	58%	78%	78%
91.6%	96%	87%	97%	94%	96%	87%	94%	94%	93%	93%	93%	92%	95%	87%	95%	79%	91%	85%	92%	89%	94%
88.9%	88%	86%	86%	86%	86%	86%	90%	96%	91%	96%	86%	86%	91%	86%	95%	98%	89%	89%	86%	86%	83%
89.0%	96%	95%	92%	95%	97%	91%	90%	96%	89%	83%	83%	87%	82%	86%	87%	88%	81%	81%	89%	85%	96%
84.2%	91%	81%	82%	90%	82%	77%	82%	88%	83%	80%	83%	76%	81%	77%	91%	93%	88%	95%	79%	81%	89%
78.0%	80%	78%	79%	82%	71%	70%	70%	81%	73%	84%	76%	76%	73%	70%	91%	89%	79%	79%	72%	85%	81%
81.7%	78%	79%	75%	87%	58%	65%	78%	88%	79%	88%	85%	90%	85%	81%	82%	88%	88%	87%	79%	90%	86%
90.1%	92%	92%	89%	94%	92%	92%	86%	88%	92%	93%	84%	93%	97%	92%	88%	91%	83%	81%	92%	92%	90%
82.8%	90%	91%	92%	93%	86%	86%	77%	91%	78%	81%	81%	91%	75%	73%	85%	75%	69%	60%	88%	88%	89%
84.8%	93%	92%	92%	93%	91%	81%	85%	92%	88%	81%	73%	93%	78%	83%	82%	87%	69%	69%	89%	80%	89%
90.3%	92%	94%	93%	91%	93%	82%	91%	92%	91%	88%	90%	86%	90%	93%	90%	92%	90%	84%	93%	91%	91%
92.0%	95%	93%	91%	94%	96%	91%	91%	96%	95%	91%	97%	77%	94%	88%	92%	94%	87%	90%	96%	96%	87%
94.8%	95%	97%	94%	93%	94%	96%	96%	93%	96%	96%	94%	96%	96%	97%	91%	93%	94%	94%	96%	93%	96%
92.1%	95%	91%	93%	91%	96%	93%	93%	94%	95%	91%	96%	93%	94%	93%	88%	87%	92%	88%	94%	86%	92%
74.2%	69%	86%	81%	81%	82%	74%	68%	45%	61%	82%	74%	65%	59%	68%	85%	78%	76%	73%	75%	88%	88%
84.5%	88%	79%	85%	87%	83%	86%	78%	80%	86%	82%	82%	85%	85%	86%	84%	82%	85%	92%	87%	84%	88%
68.4%	72%	57%	69%	59%	83%	49%	69%	71%	70%	79%	57%	50%	74%	76%	86%	85%	80%	59%	52%	80%	60%
85.7%	93%	84%	94%	96%	92%	76%	93%	97%	92%	91%	70%	71%	88%	86%	76%	82%	85%	84%	84%	78%	87%
87.5%	92%	82%	94%	94%	88%	86%	88%	85%	89%	95%	83%	86%	97%	88%	93%	89%	75%	85%	83%	79%	87%
91.0%	91%	92%	88%	91%	89%	90%	91%	96%	94%	91%	93%	86%	95%	94%	89%	93%	81%	82%	96%	96%	92%
80.3%	79%	71%	87%	80%	96%	84%	87%	81%	77%	89%	84%	62%	91%	84%	82%	75%	77%	71%	85%	80%	65%
91.6%	92%	81%	90%	89%	93%	96%	96%	95%	92%	97%	93%	93%	92%	93%	90%	92%	90%	83%	93%	91%	92%
91.9%	93%	92%	87%	91%	92%	89%	89%	98%	96%	95%	95%	77%	93%	91%	96%	94%	93%	97%	93%	96%	83%
77.3%	79%	86%	78%	78%	83%	70%	77%	72%	74%	75%	86%	78%	72%	67%	77%	79%	72%	65%	90%	83%	83%
84.1%	93%	70%	92%	90%	82%	84%	83%	93%	86%	89%	72%	71%	86%	82%	92%	74%	93%	79%	79%	85%	91%
78.1%	79%	76%	78%	81%	88%	65%	74%	84%	86%	80%	76%	60%	80%	62%	88%	94%	82%	81%	66%	86%	74%
73.8%	82%	93%	88%	83%	77%	74%	77%	66%	67%	72%	62%	62%	70%	62%	84%	84%	63%	70%	70%	66%	78%
83.5%	88%	80%	84%	89%	86%	79%	79%	95%	83%	81%	81%	92%	81%	78%	86%	74%	83%	93%	76%		81%
92.4%	94%	94%	95%	95%	93%	91%	93%	92%	93%	90%	90%	92%	92%	92%	94%	91%	88%	88%	94%	95%	94%
60.9%	64%	56%	67%	63%	78%	53%	10%	66%	78%	64%	58%	58%	78%	58%	64%	64%	64%	58%	60%	53%	64%
71.9%	72%	72%	63%	69%	73%	94%	72%	63%	59%	72%	73%	94%	73%	73%	72%	72%	72%	73%	53%	73%	72%
80.3%	84%	78%	87%	88%	74%	77%	79%	83%	82%	78%	78%	74%	77%	73%	86%	85%	82%	88%	73%	83%	78%
74.0%	91%	84%	86%	90%	61%	86%	67%	68%	55%	61%	66%	82%	67%	70%	75%	79%	73%	71%	90%	72%	61%
86.6%	90%	94%	91%	85%	79%	80%	91%	90%	87%	92%	91%	82%	98%	80%	89%	87%	81%	78%	77%	81%	95%
93.4%	92%	94%	94%	92%	88%	93%	93%	94%	94%	89%	93%	92%	96%	93%	94%	96%	96%	95%	96%	95%	93%
90.1%	97%	97%	92%	92%	85%	84%	94%	86%	93%	94%	90%	86%	93%	86%	96%	89%	77%	89%	86%	94%	92%
84.0%	92%	84%	91%	90%	92%	78%	90%	91%	82%	89%	86%	77%	90%	79%	82%	87%	81%	73%	76%	76%	77%
85.3%	94%	79%	97%	98%	78%	73%	73%	84%	87%	94%	78%	73%	79%	79%	94%	94%	94%	94%	78%	78%	94%
76.0%	85%	73%	77%	82%	84%	61%	78%	81%	85%	73%	87%	62%	80%	66%	86%	85%	77%	69%	53%	84%	67%
78.5%	79%	77%	78%	82%	72%	69%	86%	78%	81%	87%	79%	82%	80%	85%	78%	78%	78%	76%	78%	70%	75%
83.8%	77%	94%	77%	82%	52%	86%	77%	61%	85%	78%	91%	89%	91%	91%	83%	91%	89%	95%	92%	86%	92%

Model Similarity Dendrogram

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