	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	2nd 84.2%	19th 76.8%	5th 82.9%	5th 82.9%	7th 82.2%	16th 78.2%	10th 81.7%	15th 79.3%	11th 80.8%	14th 79.6%	1st 84.3%	12th 80.6%	4th 83.7%	9th 82.0%	8th 82.2%	2nd 84.2%	20th 76.8%	21st 75.3%	17th 77.8%	18th 76.8%	13th 80.2%
85.0%	91%	88%	78%	84%	93%	74%	80%	83%	83%	80%	93%	88%	92%	90%	85%	94%	81%	74%	88%	82%	83%
84.9%	80%	76%	92%	92%	63%	91%	86%	74%	68%	86%	92%	95%	94%	94%	91%	86%	85%	67%	97%	85%	89%
66.7%	66%	0%	77%	78%	69%	74%	63%	73%	71%	74%	69%	71%	71%	74%	59%	66%	72%	75%	64%	67%	67%
89.5%	93%	86%	92%	91%	91%	84%	91%	91%	90%	91%	93%	86%	93%	86%	93%	93%	89%	87%	87%	88%	84%
88.9%	93%	89%	84%	83%	83%	87%	85%	89%	87%	88%	99%	95%	98%	97%	95%	95%	97%	84%	85%	82%	72%
89.1%	87%	92%	86%	92%	92%	91%	89%	95%	92%	88%	87%	95%	96%	77%	83%	83%	91%	91%	86%	90%	89%
79.9%	79%	77%	82%	89%	85%	75%	81%	89%	95%	72%	82%	89%	84%	84%	74%	80%	62%	70%	84%	72%	73%
81.1%	81%	86%	79%	77%	69%	56%	79%	97%	96%	79%	86%	83%	77%	85%	89%	90%	88%	90%	65%	76%	76%
80.3%	89%	79%	73%	73%	76%	67%	78%	75%	78%	80%	89%	87%	84%	81%	85%	89%	85%	81%	73%	85%	79%
82.3%	88%	92%	87%	88%	87%	94%	91%	82%	86%	86%	88%	93%	90%	89%	76%	82%	77%	78%	10%	83%	82%
84.2%	91%	90%	89%	91%	82%	89%	90%	92%	84%	81%	89%	86%	78%	68%	77%	91%	74%	68%	85%	83%	90%
89.6%	93%	93%	92%	97%	92%	96%	81%	90%	83%	84%	82%	93%	91%	91%	92%	83%	88%	81%	95%	92%	92%
88.6%	90%	95%	90%	87%	91%	89%	90%	85%	90%	94%	95%	67%	92%	90%	92%	97%	76%	90%	87%	84%	90%
82.1%	89%	87%	89%	81%	94%	76%	90%	66%	79%	75%	91%	86%	81%	89%	86%	87%	68%	75%	90%	64%	81%
88.4%	92%	99%	95%	92%	88%	85%	93%	82%	88%	87%	91%	79%	93%	95%	91%	83%	84%	81%	82%	90%	87%
77.1%	87%	79%	82%	88%	79%	64%	75%	76%	69%	71%	81%	81%	83%	77%	83%	89%	59%	60%	83%	81%	73%
65.6%	73%	73%	73%	73%	70%	70%	69%	46%	58%	61%	71%	58%	56%	57%	68%	76%	52%	66%	68%	67%	73%
69.1%	71%	70%	63%	72%	65%	53%	61%	68%	61%	59%	65%	71%	74%	61%	76%	73%	79%	86%	73%	81%	70%
62.9%	78%	50%	77%	70%	71%	53%	66%	60%	60%	63%	62%	54%	65%	68%	77%	81%	60%	48%	45%	55%	57%
83.3%	77%	74%	80%	79%	89%	87%	83%	83%	95%	81%	89%	95%	88%	86%	77%	80%	73%	86%	88%	72%	88%
86.8%	89%	91%	86%	87%	93%	80%	96%	77%	92%	86%	93%	87%	91%	89%	92%	98%	75%	62%	80%	88%	91%
86.0%	85%	90%	83%	83%	89%	83%	88%	78%	90%	83%	89%	78%	88%	89%	90%	93%	87%	84%	79%	86%	92%
80.8%	76%	77%	81%	81%	87%	90%	83%	87%	77%	76%	91%	70%	83%	85%	79%	80%	78%	81%	77%	77%	81%
87.4%	89%	90%	90%	89%	91%	91%	83%	90%	89%	88%	93%	74%	94%	92%	84%	89%	87%	75%	80%	85%	93%
81.2%	88%	87%	90%	81%	91%	79%	88%	76%	78%	74%	93%	84%	79%	87%	87%	88%	61%	72%	90%	62%	71%
74.0%	83%	77%	72%	75%	79%	73%	71%	60%	69%	73%	78%	75%	79%	78%	67%	81%	70%	79%	77%	69%	68%
70.1%	79%	71%	70%	73%	74%	53%	64%	65%	70%	68%	62%	78%	72%	67%	73%	78%	76%	73%	70%	71%	66%
85.0%	92%	97%	91%	92%	97%	60%	87%	90%	92%	82%	88%	90%	86%	76%	94%	95%	87%	49%	70%	84%	86%
76.3%	84%	93%	82%	90%	80%	74%	81%	73%	74%	71%	74%	74%	70%	68%	77%	75%	74%	70%	71%	75%	73%
74.1%	71%	87%	77%	78%	79%	67%	64%	88%	70%	61%	76%	72%	66%	78%	75%	81%	86%	74%	74%	65%	67%
84.5%	88%	84%	81%	81%	92%	88%	84%	77%	81%	88%	90%	76%	86%	91%	87%	92%	76%	75%	88%	78%	92%
69.6%	74%	0%	66%	66%	74%	69%	81%	70%	72%	69%	74%	72%	72%	69%	85%	79%	71%	65%	80%	77%	77%
63.2%	65%	0%	73%	73%	65%	70%	59%	69%	66%	70%	65%	67%	67%	70%	62%	60%	68%	74%	60%	62%	62%
84.5%	90%	90%	85%	90%	89%	76%	90%	93%	89%	86%	90%	79%	81%	72%	88%	90%	93%	72%	76%	63%	93%
72.9%	88%	88%	80%	80%	46%	89%	67%	71%	73%	76%	64%	79%	90%	90%	48%	52%	74%	78%	83%	60%	54%
81.2%	85%	87%	87%	86%	68%	77%	86%	86%	86%	85%	87%	81%	89%	82%	76%	78%	80%	67%	71%	80%	82%
84.2%	90%	79%	86%	83%	93%	89%	87%	72%	83%	89%	86%	81%	92%	93%	86%	86%	80%	74%	81%	67%	92%
85.7%	91%	93%	99%	86%	87%	95%	92%	93%	92%	95%	93%	71%	97%	88%	96%	93%	48%	67%	88%	48%	87%
87.0%	93%	93%	96%	96%	87%	79%	93%	89%	91%	90%	88%	81%	89%	82%	93%	91%	70%	76%	74%	85%	91%
89.7%	97%	0%	88%	88%	96%	91%	97%	92%	95%	91%	97%	94%	94%	91%	94%	99%	93%	90%	98%	99%	99%
90.3%	98%	96%	95%	91%	92%	87%	92%	88%	86%	98%	97%	84%	90%	85%	97%	89%	87%	80%	84%	91%	90%
77.0%	75%	80%	71%	71%	78%	67%	80%	74%	75%	75%	77%	82%	87%	84%	79%	81%	73%	81%	80%	76%	72%
75.3%	63%	78%	76%	68%	79%	79%	80%	58%	70%	67%	87%	83%	79%	82%	75%	75%	68%	83%	79%	77%	75%

Model Similarity Dendrogram

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