	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 80.3%	4th 78.9%	2nd 79.4%	5th 77.7%	20th 73.0%	21st 72.6%	7th 77.2%	13th 75.3%	6th 77.7%	11th 75.7%	9th 77.0%	19th 73.9%	10th 76.7%	14th 75.3%	8th 77.2%	3rd 79.3%	15th 74.8%	16th 74.5%	12th 75.6%	17th 74.1%	18th 74.1%
76.5%	77%	76%	72%	72%	61%	77%	73%	71%	75%	73%	76%	93%	82%	85%	73%	78%	71%	87%	79%	85%	71%
85.0%	87%	89%	89%	79%	92%	86%	92%	84%	76%	75%	86%	85%	92%	85%	84%	93%	80%	81%	86%	87%	77%
66.3%	68%	66%	72%	60%	60%	72%	68%	71%	60%	72%	72%	77%	60%	68%	60%	63%	60%	77%	65%	60%	62%
88.2%	90%	83%	93%	91%	95%	80%	90%	85%	84%	95%	91%	92%	95%	81%	83%	86%	80%	81%	92%	93%	92%
92.6%	94%	95%	96%	94%	83%	92%	96%	89%	91%	100%	95%	88%	100%	97%	99%	97%	88%	84%	89%	92%	86%
91.8%	93%	93%	93%	93%	93%	94%	94%	84%	90%	92%	96%	88%	88%	82%	91%	96%	92%	96%	96%	92%	92%
78.1%	81%	76%	78%	79%	85%	75%	71%	82%	84%	80%	79%	72%	84%	80%	78%	80%	73%	77%	76%	76%	75%
80.3%	87%	84%	75%	75%	77%	60%	79%	90%	83%	79%	90%	85%	80%	79%	90%	86%	85%	75%	81%	71%	76%
80.4%	85%	77%	73%	77%	77%	68%	75%	78%	80%	83%	82%	83%	80%	78%	76%	80%	88%	96%	77%	88%	88%
88.9%	92%	88%	79%	92%	92%	92%	82%	85%	92%	91%	92%	92%	91%	92%	79%	90%	80%	90%	92%	92%	91%
67.4%	65%	76%	79%	73%	69%	80%	68%	73%	70%	63%	75%	72%	58%	58%	60%	73%	54%	45%	86%	63%	56%
81.3%	91%	81%	91%	91%	82%	76%	84%	86%	79%	69%	81%	88%	67%	75%	82%	79%	75%	76%	84%	87%	83%
80.3%	85%	82%	94%	85%	86%	83%	82%	82%	80%	80%	81%	75%	84%	78%	85%	85%	80%	74%	77%	64%	64%
72.2%	80%	83%	80%	71%	73%	60%	78%	70%	77%	79%	70%	56%	77%	63%	72%	75%	62%	71%	75%	71%	73%
66.3%	70%	72%	67%	65%	61%	66%	73%	73%	69%	62%	66%	66%	67%	67%	64%	64%	71%	66%	64%	67%	53%
72.4%	79%	72%	77%	78%	66%	73%	69%	72%	65%	73%	73%	71%	75%	78%	74%	75%	77%	61%	73%	68%	71%
63.6%	72%	85%	79%	64%	66%	61%	69%	54%	67%	60%	61%	54%	53%	62%	65%	74%	55%	56%	64%	58%	57%
71.9%	82%	69%	80%	78%	66%	53%	68%	78%	76%	66%	63%	61%	72%	68%	75%	78%	69%	86%	76%	72%	73%
67.8%	73%	57%	73%	70%	46%	56%	70%	74%	74%	82%	57%	52%	82%	80%	74%	77%	75%	62%	54%	67%	69%
70.0%	78%	72%	77%	74%	68%	68%	67%	68%	70%	68%	69%	68%	69%	70%	70%	73%	68%	68%	66%	68%	70%
80.2%	85%	85%	77%	78%	79%	70%	87%	75%	80%	80%	84%	78%	83%	85%	85%	88%	82%	77%	68%	77%	81%
76.5%	81%	82%	82%	80%	81%	66%	76%	81%	81%	77%	73%	73%	81%	75%	82%	79%	77%	69%	67%		67%
75.0%	79%	84%	84%	79%	72%	64%	73%	58%	89%	68%	85%	79%	63%	66%	74%	78%	88%	77%	69%	73%	73%
79.0%	87%	73%	92%	80%	81%	79%	83%	83%	84%	80%	77%	75%	84%	78%	86%	79%	76%	70%	73%	70%	70%
69.7%	69%	78%	69%	71%	79%	63%	77%	71%	77%	73%	75%	52%	70%	59%	68%	74%	70%	68%	70%		61%
61.9%	62%	67%	61%	69%	71%	63%	60%	51%	58%	67%	64%	66%	60%	69%	60%	66%	58%	63%	64%	42%	59%
77.2%	78%	82%	78%	74%	75%	59%	76%	79%	85%	71%	68%	79%	82%	80%	73%	79%	76%	85%	82%	84%	77%
72.1%	79%	83%	79%	76%	81%	53%	74%	79%	77%	68%	67%	67%	67%	65%	69%	80%	70%	75%	59%	68%	79%
72.3%	75%	77%	79%	74%	73%	73%	74%	62%	73%	69%	73%	73%	69%	65%	74%	70%	73%	73%	73%	73%	73%
78.1%	87%	86%	82%	82%	65%	75%	71%	83%	82%	69%	77%	85%	75%	73%	76%	83%	72%	84%	86%	75%	72%
75.4%	80%	72%	73%	77%	78%	74%	81%	71%	77%	64%	76%	75%	78%	80%	75%	79%	75%	72%	75%	71%	81%
69.4%	66%	68%	75%	75%	75%	62%	66%	63%	75%	62%	62%	58%	75%	66%	75%	73%	75%	73%	69%	75%	69%
75.9%	79%	77%	70%	70%	70%	83%	79%	82%	70%	83%	83%	87%	70%	79%	70%	79%	70%	74%	76%	70%	72%
71.1%	72%	74%	71%	70%	41%	72%	76%	75%	80%	74%	75%	68%	69%	70%	72%	76%	72%	73%	71%	68%	74%
75.1%	84%	80%	81%	85%	40%	78%	66%	69%	72%	71%	79%	78%	73%	76%	89%	70%	81%	77%	85%	77%	66%
80.4%	83%	84%	80%	87%	83%	68%	84%	81%	84%	89%	84%	66%	82%	70%	83%	84%	83%	82%	72%	78%	82%
83.5%	90%	89%	89%	84%	80%	80%	90%	81%	87%	79%	83%	80%	88%	87%	92%	90%	86%	60%	77%	76%	86%
83.2%	93%	78%	84%	84%	91%	91%	100%	89%	88%	93%	87%	75%	84%	75%	83%	78%	74%	66%	74%	66%	95%
62.1%	64%	65%	70%	70%	53%	62%	59%	60%	63%	61%	62%	62%	63%	62%	69%	66%	55%	58%	61%	56%	64%
94.3%	93%	95%	89%	98%	98%	89%	93%	90%	98%	89%	89%	84%	98%	93%	98%	100%	98%	98%	96%	98%	96%
77.1%	89%	80%	87%	88%	53%	79%	81%	78%	68%	86%	83%	63%	79%	81%	78%	79%	77%	77%	78%	61%	74%
84.8%	89%	91%	84%	78%	74%	83%	86%	86%	97%	86%	75%	76%	88%	89%	92%	89%	89%	68%	85%	97%	79%
60.9%	58%	66%	62%	51%	50%	65%	60%	44%	54%	55%	75%	62%	59%	68%	61%	67%	58%	77%	68%	62%	56%

Model Similarity Dendrogram

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