	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	1st 86.3%	13th 82.2%	3rd 85.4%	2nd 85.4%	8th 83.7%	21st 77.1%	9th 82.8%	14th 82.1%	11th 82.2%	6th 84.1%	10th 82.4%	19th 78.7%	15th 82.1%	18th 79.0%	4th 85.2%	5th 84.3%	16th 81.0%	20th 78.0%	17th 79.5%	12th 82.2%	7th 83.8%
85.0%	85%	89%	93%	88%	88%	85%	89%	82%	81%	87%	92%	77%	88%	86%	89%	86%	76%	68%	86%	80%	89%
87.6%	79%	86%	98%	92%	85%	94%	94%	85%	82%	93%	90%	87%	89%	87%	94%	86%	82%	90%	83%	88%	75%
66.7%		69%	58%	93%	48%	48%	71%	62%	58%	71%	69%	78%	69%	69%	71%	71%	71%	69%	48%	69%	71%
90.1%	93%	87%	94%	94%	93%	85%	94%	89%	87%	95%	97%	90%	96%	89%	88%	82%	82%	85%	90%	89%	94%
82.2%	83%	77%	79%	88%	77%	77%	87%	91%	81%	95%	77%	77%	77%	77%	92%	93%	81%	77%	77%	77%	87%
81.2%	87%	90%	88%	88%	83%	78%	79%	82%	80%	73%	76%	88%	77%	79%	73%	77%	80%	85%	77%		84%
82.8%	92%	78%	82%	85%	85%	73%	81%	86%	82%	81%	74%	74%	81%	74%	92%	93%	97%	87%	80%	77%	84%
72.7%	79%	67%	75%	79%	69%	58%	65%	86%	69%	83%	72%	69%	72%	63%	82%	75%	74%	77%	68%	72%	72%
80.0%	79%	79%	75%	81%	88%	70%	81%	83%	87%	83%	87%	55%	88%	73%	80%	79%	84%	84%	75%	88%	82%
84.5%	90%	94%	91%	91%	90%	90%	75%	66%	78%	80%	72%	90%	91%	90%	81%	93%	77%	61%	90%	90%	94%
83.2%	94%	92%	95%	94%	82%	87%	79%	90%	80%	80%	85%	79%	83%	69%	83%	86%	68%	67%	87%	90%	77%
87.6%	96%	94%	98%	98%	94%	84%	87%	87%	86%	86%	82%	94%	82%	89%	95%	84%	75%	64%	90%	93%	82%
90.8%	93%	92%	92%	92%	93%	85%	91%	92%	93%	87%	93%	92%	89%	93%	91%	90%	88%	86%	93%	93%	89%
90.3%	90%	86%	95%	93%	95%	88%	91%	95%	96%	93%	91%	71%	94%	85%	87%	95%	91%	87%	95%	92%	86%
93.5%	96%	96%	93%	94%	92%	94%	96%	92%	95%	96%	94%	93%	94%	95%	89%	93%	89%	85%	94%	97%	97%
91.8%	94%	87%	95%	94%	94%	90%	95%	95%	94%	93%	98%	85%	92%	89%	93%	90%	86%	88%	95%	89%	91%
72.2%		83%	74%	74%	67%	71%	64%	42%	71%	78%	75%	72%	48%	72%	73%	84%	81%	85%	70%	74%	85%
85.0%	91%	74%	85%	84%	95%	85%	80%	87%	87%	81%	84%	85%	85%	87%	86%	81%	92%	88%	78%	89%	82%
69.7%	68%	58%	65%	61%	83%	51%	69%	74%	75%	84%	77%	55%	63%	73%	85%	88%	58%	52%	51%	84%	89%
87.4%	92%	85%	93%	94%	98%	80%	96%	92%	93%	92%	89%	71%	89%	84%	81%	84%	80%	78%	94%	80%	90%
89.8%	92%	86%	94%	94%	95%	90%	92%	91%	93%	94%	91%	90%	97%	92%	90%	91%	87%	71%	86%	82%	87%
91.5%	87%	93%	86%	91%	88%	89%	90%	97%	94%	89%	87%	90%	94%	93%	92%	94%	93%	93%	91%	94%	97%
75.3%	75%	65%	73%	74%	87%	85%	87%	84%	76%	86%	86%	56%	69%	91%	67%	71%	72%	56%	77%	64%	81%
90.0%	92%	77%	91%	89%	93%	89%	98%	87%	87%	96%	90%	93%	93%	93%	88%	87%	95%	78%	90%	91%	93%
91.1%	87%	93%	92%	93%	95%	94%	91%	95%	95%	92%	94%	70%	93%	84%	93%	94%	92%	80%	94%	96%	97%
78.3%	79%	89%	85%	82%	84%	70%	82%	69%	72%	78%	85%	92%	72%	70%	78%	81%	69%	61%	85%	73%	89%
81.5%	90%	72%	87%	87%	82%	76%	82%	89%	86%	81%	70%	72%	87%	90%	87%	78%	84%	72%	75%	75%	89%
79.4%	85%	78%	80%	81%	88%	64%	74%	85%	87%	81%	79%	63%	80%	66%	93%	95%	80%	83%	67%		78%
70.1%	76%	88%	83%	80%	76%	58%	79%	59%	69%	65%	66%	56%	61%	56%	79%	70%	69%	72%	64%	77%	69%
81.9%	90%	80%	85%	86%	85%	74%	76%	84%	83%	79%	78%	90%	74%	74%	82%	75%	82%	86%	81%	88%	87%
88.5%	92%	89%	89%	89%	87%	87%	87%	88%	87%	89%	87%	85%	93%	85%	89%	90%	88%	84%	93%	92%	89%
61.3%		48%	64%	64%	43%	43%	62%	72%	77%	58%	63%	77%	77%	43%	58%	58%	62%	77%	46%	77%	58%
62.7%	64%	63%	64%	63%	63%	43%	64%	57%	53%	64%	63%	89%	63%	63%	64%	64%	60%	63%	63%	63%	64%
85.3%	87%	84%	88%	93%	89%	82%	78%	83%	87%	84%	82%	85%	82%	77%	94%	84%	94%	87%	77%	88%	86%
76.8%	89%	94%	87%	80%	74%	75%	63%	65%	60%	65%	65%	79%	71%	71%	81%	89%	76%	85%	88%	65%	90%
85.0%	89%	92%	95%	84%	85%	78%	90%	94%	89%	95%	91%	75%	92%	76%	88%	87%	78%	80%	71%	73%	83%
89.0%	89%	89%	87%	89%	90%	95%	90%	86%	90%	89%	90%	85%	91%	86%	91%	90%	91%	85%	86%	89%	90%
83.8%	87%	89%	93%	86%	84%	74%	91%	81%	90%	94%	92%	77%	80%	77%	94%	91%	73%	68%	77%	77%	85%
84.1%	92%	84%	90%	89%	90%	79%	90%	91%	81%	94%	86%	77%	87%	76%	90%	87%	83%	80%	70%	75%	76%
81.2%		69%	99%	79%	69%	77%	89%	94%	92%	89%	77%	73%	77%	63%	89%	89%	89%	77%	77%	66%	89%
77.5%	79%	72%	75%	80%	92%	65%	80%	84%	79%	77%	82%	58%	78%	67%	87%	81%	83%	81%	63%	92%	73%
79.3%	79%	82%	81%	81%	77%	67%	84%	78%	80%	83%	75%	82%	82%	88%	84%	73%	77%	80%	83%	78%	71%
87.0%		94%	87%	83%	85%	89%	79%	61%	74%	84%	89%	89%	91%	92%	99%	94%	93%	93%	94%	83%

Model Similarity Dendrogram

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