	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 81.9%	3rd 81.1%	8th 79.9%	7th 80.0%	9th 79.8%	21st 73.5%	4th 80.4%	11th 79.5%	10th 79.6%	12th 78.9%	5th 80.1%	19th 75.1%	2nd 81.2%	14th 78.7%	15th 78.3%	6th 80.0%	13th 78.7%	20th 73.8%	16th 77.5%	18th 76.2%	17th 77.0%
83.7%	86%	88%	86%	82%	87%	62%	85%	89%	85%	82%	88%	90%	89%	82%	79%	86%	83%	81%	79%	87%	82%
83.5%	81%	87%	83%	90%	61%	90%	81%	88%	68%	90%	95%	83%	93%	92%	92%	89%	93%	68%	80%	71%	79%
66.0%	61%	66%	61%	61%	66%	74%	66%	73%	70%	69%	74%	71%	65%	69%	67%	68%	63%	63%	61%	59%	59%
64.0%	60%	68%	60%	49%	71%	68%	74%	64%	60%	49%	71%	60%	71%	76%	45%	65%	59%	69%	78%	61%	66%
88.0%	85%	89%	89%	83%	79%	97%	85%	87%	84%	86%	91%	94%	86%	97%	83%	86%	90%	92%	89%	95%	82%
84.7%	84%	91%	87%	86%	91%	68%	89%	92%	90%	86%	78%	90%	89%	84%	81%	84%	81%	86%	76%	79%	86%
83.7%	87%	70%	87%	93%	85%	77%	87%	89%	90%	81%	91%	94%	81%	80%	72%	80%	94%	75%	75%	91%	78%
76.9%	81%	71%	80%	80%	77%	49%	79%	90%	80%	76%	76%	80%	76%	85%	79%	81%	83%	83%	67%	72%	69%
79.0%	82%	77%	75%	78%	79%	71%	80%	74%	79%	83%	79%	83%	82%	84%	77%	85%	87%	75%	77%	75%	76%
57.4%	59%	64%	47%	44%	66%	72%	69%	60%	56%	44%	68%	43%	56%	63%	45%	58%	61%	53%	81%	50%	47%
84.9%	92%	92%	92%	85%	82%	92%	91%	92%	86%	90%	79%	76%	90%	68%	87%	92%	69%	63%	89%	86%	90%
53.4%	58%	65%	45%	45%	57%	60%	56%	48%	55%	37%	66%	41%	60%	62%	39%	46%	60%	49%	76%	48%	49%
88.6%	96%	95%	96%	94%	93%	88%	89%	79%	91%	94%	84%	67%	94%	86%	95%	95%	84%	75%	87%	86%	92%
88.9%	96%	91%	92%	94%	86%	91%	93%	89%	87%	91%	87%	77%	97%	97%	92%	93%	76%	71%	86%	88%	93%
87.2%	92%	95%	94%	94%	95%	76%	85%	90%	88%	91%	86%	78%	95%	88%	93%	89%	86%	73%	82%	81%	80%
78.1%	81%	78%	84%	87%	79%	70%	82%	85%	79%	75%	81%	77%	81%	78%	75%	76%	81%	72%	71%	74%	74%
66.6%	72%	72%	72%	77%	74%	66%	60%	58%	64%	70%	60%	71%	57%	55%	75%	74%	58%	62%	69%	60%	72%
66.6%	70%	70%	64%	75%	67%	41%	66%	72%	67%	60%	70%	71%	68%	65%	64%	60%	71%	71%	61%	75%	71%
74.8%	77%	75%	80%	80%	64%	61%	89%	74%	72%	75%	74%	68%	83%	75%	71%	68%	86%	68%	69%	90%	71%
84.2%	85%	69%	85%	83%	88%	90%	85%	96%	98%	82%	92%	89%	85%	81%	77%	79%	88%	77%	82%	78%	79%
87.3%	94%	91%	91%	90%	95%	70%	97%	95%	94%	88%	84%	82%	92%	82%	92%	91%	83%	79%	78%	82%	83%
85.0%	91%	87%	89%	86%	83%	73%	91%	85%	88%	88%	91%	83%	89%	86%	85%	86%	85%	78%	77%	79%	85%
79.4%	89%	83%	85%	86%	79%	72%	80%	73%	81%	80%	75%	45%	79%	78%	89%	90%	75%	85%	86%	76%	82%
87.4%	95%	93%	92%	91%	93%	82%	96%	92%	87%	93%	88%	73%	93%	88%	84%	87%	84%	74%	80%	86%	84%
89.8%	98%	89%	92%	93%	91%	90%	90%	87%	84%	90%	89%	76%	91%	94%	95%	94%	90%	86%	87%	88%	92%
79.1%	86%	77%	77%	76%	83%	71%	74%	67%	77%	83%	82%	69%	81%	84%	85%	87%	77%	78%	79%	82%	87%
69.2%	73%	71%	73%	73%	75%	50%	66%	74%	74%	69%	65%	74%	72%	62%	70%	69%	67%	67%	63%	74%	72%
86.3%	89%	95%	86%	95%	97%	69%	97%	93%	91%	92%	83%	79%	87%	68%	95%	91%	84%	82%	71%	79%	90%
58.2%	57%	72%	61%	63%	62%	56%	61%	46%	55%	49%	67%	39%	60%	57%	57%	63%	64%	61%	73%		40%
68.7%	60%	68%	72%	73%	67%	65%	59%	63%	70%	64%	78%	74%	63%	69%	63%	63%	82%	83%	73%	69%	65%
85.7%	92%	87%	81%	81%	86%	80%	83%	83%	84%	91%	83%	74%	88%	90%	94%	94%	84%	83%	88%	85%	89%
77.6%	81%	78%	83%	83%	78%	69%	78%	71%	73%	74%	69%	72%	79%	74%	82%	75%	81%	79%	83%	85%	82%
61.9%	56%	61%	57%	57%	61%	70%	61%	68%	66%	65%	70%	67%	60%	65%	63%	64%	59%	60%	56%	55%	58%
83.2%	87%	72%	85%	85%	94%	73%	80%	92%	92%	91%	83%	88%	84%	72%	82%	87%	89%	77%	69%		82%
64.0%	72%	79%	63%	63%	53%	62%	55%	59%	59%	60%	63%	62%	75%	81%	55%	58%	63%	68%	88%	60%	47%
78.6%	82%	87%	82%	81%	66%	80%	86%	86%	77%	79%	76%	81%	82%	80%	85%	74%	80%	54%	81%	71%	81%
84.7%	97%	87%	82%	82%	90%	84%	86%	77%	86%	92%	80%	75%	88%	88%	84%	87%	81%	71%	83%	85%	94%
88.9%	92%	90%	96%	93%	90%	89%	91%	92%	92%	91%	93%	74%	93%	74%	99%	98%	80%	80%	78%	89%	93%
84.0%	94%	90%	92%	88%	92%	66%	93%	91%	88%	91%	85%	83%	87%	72%	94%	91%	86%	60%	72%	72%	78%
95.9%	98%	100%	95%	95%	100%	91%	100%	93%	95%	97%	91%	94%	99%	97%	96%	97%	97%	97%	95%	93%	93%
87.7%	95%	93%	86%	87%	91%	81%	90%	89%	88%	96%	94%	93%	89%	86%	90%	90%	90%	84%	80%	63%	87%
71.8%	70%	75%	68%	68%	74%	68%	69%	72%	80%	72%	75%	80%	81%	86%	59%	67%	72%	71%	74%	62%	65%
86.2%	88%	90%	90%	92%	85%	86%	85%	83%	91%	85%	92%	88%	83%	82%	82%	84%	79%	90%	83%	84%	89%

Model Similarity Dendrogram

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