	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 83.1%	6th 80.6%	3rd 82.6%	2nd 83.0%	9th 78.7%	21st 70.4%	11th 78.2%	8th 79.8%	12th 78.2%	7th 80.0%	15th 77.0%	13th 77.5%	10th 78.4%	19th 74.5%	5th 81.8%	4th 82.0%	16th 76.6%	18th 74.5%	14th 77.0%	20th 74.2%	17th 74.6%
81.8%		85%	83%	89%	81%	67%	82%	86%	78%	80%	82%	88%	84%	83%	80%	88%	74%	86%	82%	83%	75%
75.6%	73%	65%	79%	87%	40%	85%	65%	77%	58%	82%	87%	88%	82%	82%	88%	84%	78%	68%	83%	65%	71%
63.8%		61%	66%	66%	62%	67%	62%	69%	54%	71%	69%	66%	66%	66%	63%	59%	56%	66%	63%	62%	62%
87.5%	85%	86%	90%	90%	90%	86%	88%	88%	88%	89%	82%	90%	89%	82%	89%	86%	85%	89%	88%	89%	88%
90.2%		90%	85%	90%	87%	79%	87%	94%	87%	99%	96%	94%	99%	97%	94%	96%	95%	80%	84%	97%	73%
86.4%		93%	95%	93%	89%	88%	90%	87%	88%	89%	85%	69%	82%	79%	86%	89%	87%	90%	88%	74%	88%
79.5%	83%	81%	78%	82%	85%	72%	73%	83%	80%	82%	73%	81%	72%	85%	82%	82%	79%	86%	70%	79%	81%
75.4%	79%	73%	71%	84%	82%	42%	72%	80%	75%	70%	76%	78%	74%	71%	89%	76%	87%	89%	78%	73%	65%
84.0%	74%	88%	87%	82%	96%	67%	86%	86%	89%	91%	84%	92%	92%	84%	81%	87%	93%	85%	81%	69%	69%
90.7%	90%	90%	97%	94%	90%	98%	89%	84%	90%	94%	90%	93%	90%	90%	92%	93%	78%	90%	90%	89%	94%
84.7%		88%	88%	95%	88%	84%	85%	76%	90%	89%	88%	89%	78%	89%	86%	89%	79%	73%	74%	86%	81%
83.9%	88%	84%	93%	94%	90%	93%	83%	93%	90%	77%	72%	93%	59%	68%	85%	92%	85%	50%	94%	85%	93%
86.2%	81%	90%	88%	92%	86%	87%	85%	89%	84%	85%	90%	87%	87%	88%	88%	87%	84%	84%	81%	84%	84%
88.8%	92%	90%	91%	93%	91%	79%	90%	93%	93%	97%	91%	73%	94%	76%	92%	90%	83%	85%	95%	88%	89%
81.5%	94%	81%	93%	90%	80%	67%	89%	86%	88%	84%	81%	90%	78%	75%	81%	84%	90%	63%	75%	78%	65%
75.7%	88%	82%	88%	89%	79%	57%	78%	79%	74%	78%	71%	72%	75%	67%	77%	85%	78%	58%	74%	78%	63%
61.7%		68%	67%	69%	68%	54%	64%	52%	62%	60%	54%	61%	59%	53%	62%	77%	54%	67%	64%	54%	65%
67.8%	86%	66%	84%	83%	71%	48%	57%	72%	65%	57%	58%	65%	71%	59%	74%	73%	63%	67%	74%	60%	71%
63.6%	78%	52%	72%	56%	73%	40%	56%	68%	64%	88%	60%	46%	82%	64%	86%	79%	52%	49%	49%	70%	52%
76.6%	77%	84%	75%	85%	82%	71%	83%	73%	71%	83%	72%	70%	77%	72%	91%	84%	70%	68%	73%	72%	75%
84.5%	89%	89%	88%	86%	91%	66%	86%	92%	92%	81%	85%	93%	84%	74%	93%	96%	85%	76%	73%	86%	69%
80.0%	79%	81%	76%	79%	85%	67%	82%	84%	85%	79%	74%	84%	80%	81%	85%	88%	83%	85%	69%	75%	78%
78.2%	82%	76%	85%	76%	92%	87%	88%	85%	70%	87%	79%	83%	68%	66%	76%	72%	72%	82%	85%	63%	68%
88.4%	85%	88%	92%	91%	87%	91%	88%	91%	90%	86%	90%	86%	89%	87%	90%	92%	87%	87%	85%	87%	87%
84.7%	82%	85%	87%	85%	85%	81%	88%	90%	88%	87%	81%	72%	87%	77%	83%	90%	84%	87%	92%	85%	83%
69.2%	69%	68%	75%	67%	59%	66%	69%	62%	71%	68%	75%	73%	70%	78%	66%	71%	70%	64%	74%	75%	64%
64.7%	79%	67%	71%	77%	75%	45%	57%	67%	68%	63%	53%	70%	65%	56%	69%	61%	71%	67%	56%	65%	56%
73.1%	86%	88%	81%	80%	81%	52%	74%	75%	83%	77%	64%	63%	70%	56%	87%	78%	61%	78%	65%	64%	73%
70.9%	80%	89%	80%	81%	63%	64%	72%	65%	66%	64%	64%	72%	72%	62%	69%	79%	68%	66%	63%	76%	73%
75.5%		86%	87%	94%	80%	62%	63%	87%	77%	74%	77%	62%	76%	65%	75%	82%	63%	75%	86%	76%	64%
81.2%	85%	84%	87%	88%	88%	65%	84%	83%	84%	76%	76%	86%	85%	71%	87%	89%	80%	78%	73%		74%
82.7%		86%	80%	80%	85%	80%	85%	77%	93%	75%	77%	80%	80%	80%	93%	82%	91%	76%	84%	84%	85%
58.1%		56%	62%	62%	58%	62%	58%	65%	50%	67%	64%	62%	62%	62%	52%	60%	52%	56%	59%	34%	58%
77.1%	85%	76%	81%	81%	80%	63%	74%	77%	77%	82%	73%	74%	75%	73%	79%	83%	79%	79%	71%	79%	78%
79.9%	90%	91%	91%	89%	51%	71%	73%	75%	73%	76%	71%	85%	83%	79%	89%	76%	88%	86%	91%	74%	76%
85.7%	93%	87%	99%	99%	56%	80%	92%	90%	85%	88%	91%	77%	91%	78%	86%	90%	89%	77%	80%	79%	93%
77.0%	81%	88%	81%	79%	91%	60%	84%	79%	79%	73%	80%	71%	80%	72%	83%	73%	71%	74%	73%	73%	71%
82.0%		77%	95%	86%	86%	84%	88%	86%	84%	90%	85%	74%	86%	81%	87%	88%	74%	70%	98%	42%	79%
72.6%	91%	77%	77%	77%	68%	53%	80%	84%	73%	83%	77%	75%	73%	55%	76%	82%	79%	67%	57%	62%	58%
95.0%		92%	98%	98%	93%	98%	93%	99%	85%	97%	99%	98%	98%	98%	97%	97%	87%	98%	95%	85%	94%
74.8%	75%	82%	69%	69%	76%	65%	79%	85%	89%	74%	76%	62%	75%	72%	80%	80%	79%	33%	83%	85%	82%
77.2%	78%	79%	77%	75%	79%	66%	78%	72%	79%	83%	73%	77%	76%	84%	83%	77%	78%	75%	74%	77%	82%
63.6%		78%	63%	67%	67%	67%	65%	48%	55%	67%	67%	67%	58%	67%	67%	59%	51%	76%	67%	57%	60%

Model Similarity Dendrogram

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