	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
Score	3rd 82.9%	10th 81.1%	5th 82.7%	2nd 83.3%	13th 80.4%	21st 77.3%	13th 80.4%	11th 80.9%	7th 81.9%	4th 82.8%	12th 80.6%	20th 77.3%	8th 81.7%	19th 77.5%	1st 84.3%	6th 82.7%	15th 80.2%	18th 78.0%	17th 78.8%	9th 81.2%	16th 80.0%
83.5%	82%	86%	88%	85%	83%	87%	82%	83%	90%	83%	89%	79%	83%	78%	86%	83%	81%	75%	85%	83%	82%
68.5%	62%	72%	68%	68%	60%	81%	72%	69%	55%	66%	68%	87%	71%	78%	72%	62%	75%	66%	72%	65%	49%
67.7%	69%	70%	58%	72%	68%	68%	94%	58%	58%	69%	68%	73%	68%	68%	69%	69%	70%	68%	48%	68%	69%
86.5%	86%	86%	88%	89%	91%	90%	88%	84%	78%	87%	89%	90%	89%	82%	87%	80%	84%	84%	89%	90%	86%
82.2%	83%	79%	81%	81%	79%	79%	79%	86%	85%	89%	79%	79%	79%	79%	90%	94%	82%	79%	79%	79%	87%
86.8%	93%	97%	95%	95%	99%	89%	85%	87%	87%	86%	82%	86%	85%	82%	87%	87%	83%	88%	83%	66%	81%
82.4%	91%	87%	84%	86%	85%	74%	80%	93%	80%	78%	79%	74%	79%	79%	89%	91%	82%	84%	77%	77%
75.4%	79%	66%	74%	84%	77%	65%	74%	82%	73%	81%	69%	77%	77%	66%	79%	86%	73%	76%	71%	75%	80%
75.2%	71%	56%	76%	73%	82%	76%	81%	85%	86%	78%	56%	56%	85%	56%	74%	75%	78%	95%	75%	85%	81%
89.9%	90%	90%	97%	95%	90%	90%	88%	66%	91%	93%	93%	93%	89%	90%	92%	92%	90%	86%	90%	89%	94%
83.3%	95%	85%	85%	95%	92%	88%	89%	84%	86%	76%	90%	86%	77%	72%	85%	89%	74%	56%	90%	81%	75%
85.0%	91%	89%	91%	90%	93%	77%	73%	94%	92%	88%	87%	93%	94%	68%	89%	91%	73%	61%	90%	79%	83%
90.4%	90%	92%	91%	93%	93%	90%	93%	93%	89%	93%	93%	93%	92%	93%	91%	87%	83%	85%	93%	88%	84%
89.9%	89%	95%	90%	90%	94%	79%	94%	87%	94%	88%	93%	74%	92%	88%	94%	90%	94%	92%	93%	93%	84%
92.5%	92%	91%	94%	93%	90%	94%	96%	97%	94%	93%	92%	93%	93%	93%	92%	94%	91%	88%	92%	93%	87%
88.2%	90%	86%	91%	90%	90%	86%	91%	90%	93%	89%	87%	68%	90%	90%	89%	89%	97%	84%	94%	79%	90%
76.5%	75%	89%	89%	89%	89%	81%	64%	56%	79%	86%	74%	69%	64%	65%	78%	84%	76%	76%	85%	85%	53%
85.9%	92%	80%	89%	90%	78%	82%	87%	88%	90%	85%	91%	61%	84%	86%	87%	88%	88%	93%	88%	90%	87%
64.8%	75%	52%	63%	56%	64%	45%	53%	61%	61%	85%	59%	46%	83%	62%	83%	79%	77%	59%	50%	78%	69%
82.7%	81%	92%	90%	89%	81%	73%	93%	87%	92%	80%	84%	71%	81%	78%	94%	90%	83%	74%	70%	75%	78%
84.0%	90%	82%	93%	96%	90%	86%	10%	83%	87%	93%	90%	87%	94%	85%	91%	90%	80%	83%	82%	82%	89%
87.2%	86%	88%	84%	87%	89%	84%	86%	91%	86%	87%	84%	87%	88%	85%	89%	88%	88%	83%	89%	92%	90%
77.7%	82%	76%	84%	76%	74%	73%	88%	84%	78%	87%	86%	63%	84%	70%	75%	72%	71%	79%	77%		75%
91.4%	91%	81%	91%	94%	93%	91%	92%	95%	93%	94%	96%	93%	93%	93%	90%	92%	92%	94%	93%	93%	75%
90.6%	92%	88%	86%	88%	93%	90%	92%	94%	95%	90%	92%	78%	96%	90%	95%	94%	87%	86%	93%	93%	90%
75.9%	78%	84%	76%	75%	85%	67%	76%	71%	75%	75%	74%	76%	71%	62%	80%	79%	70%	65%	85%	85%	85%
77.4%	85%	64%	86%	81%	80%	76%	76%	83%	73%	81%	62%	67%	78%	81%	84%	75%	78%	75%	77%	78%	86%
79.8%	84%	80%	81%	84%	74%	69%	80%	86%	85%	78%	77%	85%	78%	67%	85%	83%	83%	81%	74%	81%	81%
71.2%	76%	91%	80%	81%	73%	74%	73%	65%	73%	65%	63%	63%	66%	65%	79%	69%	65%	63%	63%	76%	72%
84.7%	93%	87%	92%	91%	88%	74%	88%	89%	78%	88%	84%	78%	78%	78%	91%	84%	84%	82%	85%	78%	88%
91.3%	94%	93%	91%	93%	91%	84%	90%	93%	89%	94%	89%	89%	92%	89%	94%	94%	94%	87%	92%	91%	94%
61.0%	59%	44%	64%	54%	78%	44%	63%	76%	78%	59%	78%	44%	59%	44%	59%	59%	59%	78%	46%	78%	59%
63.2%	64%	64%	53%	64%	44%	63%	94%	49%	54%	64%	63%	69%	63%	94%	64%	64%	64%	63%	44%	63%	64%
77.5%	79%	72%	78%	82%	80%	74%	75%	81%	82%	80%	74%	70%	73%	78%	82%	83%	81%	76%	70%	79%	79%
81.5%	91%	88%	82%	92%	63%	73%	79%	77%	76%	77%	73%	85%	85%	86%	91%	89%	88%	63%	88%	78%	88%
87.1%	94%	95%	93%	88%	80%	84%	92%	78%	90%	91%	88%	85%	95%	81%	86%	79%	81%	83%	85%		95%
87.4%	87%	86%	85%	88%	85%	88%	84%	88%	85%	87%	89%	89%	86%	87%	89%	89%	91%	92%	87%	89%	84%
83.6%	87%	88%	83%	86%	79%	80%	86%	81%	90%	92%	85%	79%	85%	79%	91%	82%	68%	86%	79%	79%	90%
79.2%	86%	82%	84%	83%	74%	75%	82%	86%	78%	86%	81%	74%	87%	75%	79%	78%	76%	75%	73%	75%	74%
83.4%	69%	90%	98%	73%	68%	78%	90%	85%	92%	90%	78%	94%	78%	63%	90%	90%	89%	78%	78%	90%	90%
70.5%	77%	64%	67%	69%	75%	60%	63%	82%	79%	71%	77%	57%	69%	69%	75%	75%	71%	72%	60%	72%	77%
73.2%	76%	74%	74%	74%	73%	65%	76%	75%	77%	80%	71%	77%	75%	81%	74%	68%	73%	63%	73%	77%	62%
76.9%	68%	85%	69%	82%	49%	78%	65%	58%	77%	80%	89%	89%	87%	77%	83%	80%	83%	77%	83%	84%	72%

Model Similarity Dendrogram

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