	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	5th 78.4%	1st 79.5%	8th 77.5%	7th 78.2%	9th 77.4%	21st 71.5%	6th 78.4%	3rd 79.0%	11th 77.0%	15th 76.3%	2nd 79.1%	16th 76.1%	4th 78.7%	13th 76.8%	18th 75.5%	10th 77.4%	12th 76.9%	14th 76.3%	17th 75.5%	19th 74.1%	20th 71.7%
74.3%	75%	79%	69%	71%	75%	55%	74%	78%	75%	74%	83%	80%	81%	77%	69%	77%	68%	84%	70%	72%	75%
79.1%	91%	83%	83%	87%	74%	79%	84%	83%	67%	84%	77%	75%	80%	79%	85%	80%	77%	66%	81%	74%	72%
65.0%	59%	61%	61%	61%	76%	74%	61%	72%	64%	68%	69%	72%	59%	69%	65%	65%	66%	63%	61%	59%	59%
66.5%	73%	69%	60%	60%	69%	69%	78%	63%	60%	56%	75%	60%	69%	71%	59%	64%	74%	69%	74%	67%	57%
90.0%	90%	92%	88%	83%	80%	98%	83%	87%	90%	89%	96%	94%	95%	96%	89%	89%	93%	92%	96%	92%	78%
80.9%	79%	94%	91%	86%	82%	64%	85%	83%	88%	84%	71%	87%	85%	69%	82%	86%	78%	89%	68%	62%	86%
83.3%	83%	77%	76%	83%	83%	75%	81%	90%	88%	83%	85%	96%	87%	77%	74%	78%	96%	96%	86%	71%	84%
75.5%	81%	69%	68%	70%	73%	52%	76%	78%	79%	76%	79%	86%	78%	92%	75%	72%	84%	80%	71%	79%	67%
91.2%	94%	88%	87%	87%	95%	89%	87%	96%	89%	91%	93%	94%	92%	92%	88%	97%	92%	91%	88%	98%	88%
68.1%	70%	79%	57%	67%	71%	75%	81%	67%	61%	62%	68%	54%	73%	74%	57%	64%	73%	80%	78%	66%	53%
81.0%	86%	87%	90%	89%	75%	89%	87%	86%	82%	84%	87%	64%	82%	72%	84%	82%	65%	51%	85%	87%	87%
69.6%	67%	85%	53%	70%	76%	80%	61%	68%	66%	55%	78%	59%	70%	79%	58%	59%	75%	72%	85%	72%	74%
78.6%	73%	79%	79%	73%	79%	71%	86%	82%	83%	76%	78%	76%	87%	87%	77%	78%	87%	76%	76%	72%	75%
84.6%	83%	92%	87%	83%	78%	79%	89%	78%	82%	78%	82%	81%	90%	89%	86%	90%	78%	91%	92%	83%	86%
76.0%	72%	78%	83%	75%	68%	64%	82%	73%	91%	73%	81%	85%	81%	80%	73%	74%	78%	72%	75%	73%	66%
69.7%	75%	72%	73%	74%	80%	53%	70%	77%	70%	68%	76%	72%	71%	66%	65%	68%	73%	60%	61%	69%	71%
54.0%	56%	57%	56%	60%	68%	58%	53%	42%	55%	53%	48%	55%	45%	47%	70%	62%	45%	45%	55%	48%	55%
62.8%	67%	68%	62%	70%	62%	40%	62%	66%	66%	62%	68%	69%	64%	56%	56%	60%	68%	68%	55%	63%	67%
70.3%	75%	79%	71%	79%	58%	64%	89%	70%	68%	68%	71%	69%	75%	72%	69%	71%	69%	61%	68%	77%	54%
81.6%	75%	63%	78%	82%	82%	89%	80%	92%	91%	82%	88%	88%	80%	79%	66%	73%	92%	89%	86%	80%	79%
83.7%	88%	90%	86%	82%	83%	67%	92%	92%	89%	83%	92%	84%	91%	82%	80%	89%	83%	84%	75%	68%	78%
84.1%	85%	81%	81%	81%	87%	70%	89%	82%	88%	83%	87%	94%	89%	89%	81%	85%	87%	84%	76%	84%	84%
71.8%	84%	73%	69%	73%	73%	66%	82%	79%	70%	72%	78%	54%	70%	69%	78%	79%	68%	65%	71%	63%	72%
78.9%	84%	77%	83%	79%	76%	72%	83%	80%	84%	77%	76%	70%	82%	83%	78%	81%	76%	79%	79%	76%	82%
79.0%	81%	86%	78%	75%	76%	75%	74%	78%	77%	76%	84%	78%	82%	78%	81%	79%	75%	76%	86%	83%	81%
74.7%	83%	73%	78%	79%	76%	72%	68%	71%	72%	79%	75%	65%	79%	77%	81%	74%	76%	78%	73%	67%	72%
74.9%	84%	75%	74%	78%	76%	60%	73%	74%	78%	76%	71%	76%	74%	73%	74%	76%	73%	84%	67%	82%	75%
80.1%	80%	85%	80%	85%	91%	65%	82%	93%	87%	86%	78%	82%	83%	63%	91%	78%	77%	82%	69%	72%	73%
64.8%	68%	84%	71%	74%	60%	61%	71%	76%	38%	61%	69%	36%	67%	63%	65%	67%	63%	71%	71%	67%	58%
65.9%	56%	73%	69%	67%	58%	68%	56%	60%	65%	65%	74%	66%	63%	74%	59%	65%	71%	76%	70%	65%	64%
80.2%	82%	80%	84%	81%	74%	68%	89%	83%	82%	81%	83%	86%	80%	79%	79%	80%	79%	78%	78%	84%	75%
94.6%	98%	100%	99%	100%	84%	86%	100%	88%	97%	92%	91%	88%	98%	91%	95%	92%	94%	97%	100%	98%	98%
62.0%	56%	58%	58%	58%	72%	71%	58%	69%	61%	65%	66%	69%	56%	66%	61%	65%	60%	60%	58%	60%	56%
84.4%	86%	79%	88%	92%	91%	71%	73%	84%	81%	92%	87%	80%	80%	80%	90%	89%	96%	87%	73%	90%	84%
61.4%	68%	75%	60%	64%	52%	55%	54%	60%	56%	56%	57%	69%	69%	69%	58%	62%	64%	51%	74%	68%	48%
79.2%	89%	88%	90%	81%	83%	78%	87%	93%	72%	78%	79%	77%	83%	77%	72%	72%	70%	74%	75%	67%	78%
71.6%	69%	74%	74%	73%	64%	62%	78%	78%	79%	72%	73%	79%	77%	67%	75%	80%	64%	71%	65%	64%	66%
88.8%	89%	91%	95%	97%	95%	80%	96%	95%	92%	92%	97%	75%	93%	85%	92%	93%	81%	94%	79%	66%	88%
83.2%	86%	79%	93%	90%	92%	64%	84%	83%	86%	87%	85%	85%	89%	72%	93%	89%	86%	85%	68%	83%	69%
81.0%	75%	77%	77%	77%	92%	91%	77%	88%	80%	85%	86%	88%	75%	86%	75%	85%	82%	79%	77%	75%	75%
79.7%	84%	81%	89%	88%	88%	75%	87%	86%	82%	88%	80%	81%	85%	78%	87%	87%	67%	79%	72%	79%	31%
87.0%	86%	93%	89%	89%	96%	89%	90%	89%	93%	84%	87%	91%	90%	91%	73%	87%	91%	77%	86%	84%	73%
86.6%	88%	97%	95%	91%	87%	92%	79%	83%	86%	86%	93%	85%	83%	86%	81%	84%	91%		94%	79%	72%

Model Similarity Dendrogram

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