	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	4th 82.9%	6th 82.3%	7th 81.8%	5th 82.6%	12th 80.4%	21st 75.3%	10th 81.1%	9th 81.4%	11th 80.6%	13th 79.8%	2nd 83.1%	18th 76.9%	8th 81.7%	16th 77.8%	3rd 83.0%	1st 84.9%	14th 79.5%	18th 76.9%	15th 78.8%	17th 77.4%	20th 75.9%
85.0%	83%	86%	72%	77%	84%	61%	84%	92%	89%	79%	91%	88%	90%	85%	89%	91%	94%	81%	83%	94%	92%
88.4%	94%	89%	95%	93%	66%	96%	95%	87%	74%	91%	96%	89%	94%	86%	91%	94%	95%	84%	90%	74%	83%
71.0%	66%	67%	78%	70%	60%	75%	67%	73%	64%	75%	75%	72%	68%	70%	70%	75%	80%	84%	62%	70%	70%
86.0%	91%	84%	89%	93%	85%	79%	91%	80%	84%	91%	88%	86%	91%	75%	88%	87%	86%	89%	81%	87%	81%
90.1%	97%	95%	94%	97%	81%	91%	94%	85%	89%	87%	91%	83%	92%	91%	94%	89%	98%	82%	97%	74%	92%
89.9%	96%	97%	94%	97%	91%	97%	92%	86%	89%	92%	93%	86%	92%	86%	86%	97%	89%	95%	94%	69%	69%
85.7%	81%	84%	82%	93%	90%	79%	82%	90%	91%	78%	90%	80%	82%	77%	83%	91%	92%	94%	91%	84%	85%
75.9%	71%	71%	73%	71%	75%	50%	72%	84%	84%	77%	76%	77%	74%	70%	83%	84%	81%	73%	68%	87%	92%
83.9%	88%	84%	80%	84%	83%	72%	82%	81%	80%	91%	87%	93%	87%	85%	83%	87%	88%	77%	86%	82%	81%
89.8%	95%	85%	94%	96%	93%	88%	93%	87%	88%	95%	92%	93%	94%	86%	89%	95%	83%	81%	84%	87%	87%
74.4%	85%	75%	85%	85%	56%	83%	71%	82%	77%	62%	78%	72%	72%	73%	76%	76%	60%	58%	88%	83%	65%
79.2%	85%	81%	80%	83%	82%	80%	77%	86%	80%	78%	79%	76%	78%	79%	78%	79%	77%	71%	79%	77%	79%
84.7%	91%	93%	90%	91%	88%	89%	86%	77%	88%	94%	92%	63%	87%	91%	89%	91%	88%	80%	83%	81%	47%
83.0%	82%	81%	79%	81%	91%	82%	86%	83%	85%	80%	89%	73%	85%	89%	83%	89%	73%	89%	90%	78%	75%
84.0%	80%	91%	87%	87%	82%	81%	90%	84%	87%	80%	89%	79%	82%	84%	84%	87%	87%	84%	80%	82%	76%
83.2%	86%	84%	86%	90%	92%	63%	84%	85%	79%	76%	84%	64%	84%	75%	90%	95%	91%	87%	79%	88%	86%
68.0%	71%	84%	87%	72%	67%	56%	67%	55%	64%	67%	69%	65%	59%	62%	79%	79%	51%	68%	68%	67%	71%
57.3%	64%	53%	55%	64%	56%	42%	46%	66%	59%	53%	50%	47%	61%	48%	66%	61%	64%	61%	53%	65%	69%
53.8%	58%	39%	64%	58%	63%	45%	61%	48%	50%	62%	56%	39%	52%	46%	77%	65%	46%	52%	40%	61%	47%
84.0%	74%	75%	73%	83%	94%	93%	84%	87%	91%	80%	90%	86%	89%	82%	78%	86%	86%	86%	89%	94%	64%
82.4%	83%	83%	81%	81%	82%	71%	89%	89%	85%	81%	84%	83%	82%	83%	90%	89%	76%	75%	75%	78%	90%
82.1%	84%	85%	78%	77%	87%	82%	89%	86%	85%	84%	85%	82%	90%	85%	84%	90%	85%	80%	75%	81%	51%
77.1%	74%	74%	79%	79%	83%	73%	83%	85%	76%	75%	82%	77%	75%	77%	74%	78%	77%	74%	78%	76%	70%
82.2%	88%	90%	92%	91%	86%	81%	83%	81%	87%	85%	90%	71%	90%	82%	82%	88%	83%	73%	80%	63%	60%
78.3%	81%	78%	78%	75%	83%	79%	81%	75%	82%	74%	90%	69%	77%	80%	75%	86%	71%	82%	88%	69%	71%
79.3%	91%	83%	80%	81%	85%	72%	82%	71%	83%	89%	87%	82%	87%	81%	72%	91%	59%	69%	82%	67%	71%
73.5%	80%	68%	69%	72%	71%	50%	65%	82%	72%	70%	67%	69%	76%	55%	85%	83%	86%	84%	71%	84%	84%
82.4%	87%	89%	82%	88%	95%	62%	83%	91%	86%	81%	83%	78%	80%	68%	92%	90%	80%	84%	76%	84%	71%
74.9%	88%	88%	85%	88%	80%	73%	79%	70%	70%	69%	71%	67%	69%	66%	77%	77%	69%	73%	69%	72%	72%
75.0%	79%	85%	83%	80%	85%	64%	63%	82%	76%	68%	78%	67%	72%	66%	76%	75%	73%	78%	73%	74%	79%
84.9%	90%	91%	83%	82%	91%	85%	84%	80%	86%	85%	90%	79%	90%	90%	88%	94%	73%	69%	85%	79%	89%
78.7%	85%	84%	72%	81%	92%	76%	84%	78%	87%	76%	76%	79%	83%	81%	81%	76%	71%	67%	90%	61%	73%
67.2%	63%	63%	75%	66%	56%	71%	63%	69%	61%	71%	71%	68%	64%	66%	66%	71%	76%	80%	58%		66%
81.4%	85%	83%	80%	85%	91%	70%	83%	86%	92%	81%	79%	76%	73%	75%	88%	90%	89%	81%	70%	71%	82%
76.4%	90%	84%	77%	76%	60%	90%	83%	85%	78%	75%	74%	93%	87%	73%	72%	74%	67%	58%	68%	78%	62%
83.0%	93%	91%	94%	90%	71%	78%	91%	95%	89%	94%	85%	78%	91%	72%	76%	76%	79%	75%	70%	75%	79%
87.0%	89%	94%	88%	88%	91%	80%	95%	81%	88%	91%	90%	85%	93%	93%	89%	90%	91%	69%	80%	84%	77%
87.8%	82%	94%	92%	91%	85%	95%	85%	93%	85%	84%	90%	79%	87%	87%	96%	99%	87%	87%	94%	59%	92%
82.4%	84%	82%	82%	84%	88%	73%	87%	87%	83%	76%	82%	83%	84%	75%	90%	88%	87%	84%	70%	81%	80%
95.0%	94%	95%	93%	98%	87%	97%	95%	99%	92%	97%	97%	100%	96%	98%	98%	97%	92%	87%	89%		98%
83.2%	93%	90%	90%	94%	78%	65%	90%	94%	81%	89%	88%	68%	90%	77%	92%	90%	82%	34%	91%	89%	83%
84.9%	84%	83%	76%	80%	83%	71%	76%	87%	80%	78%	93%	85%	96%	97%	92%	84%	93%	90%	89%	91%	75%
73.0%	61%	83%	71%	61%	67%	78%	70%	56%	69%	70%	87%	79%	70%	80%	78%	78%	62%	79%	82%	73%	78%

Model Similarity Dendrogram

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