	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	3rd 79.3%	12th 77.3%	2nd 79.6%	1st 80.0%	4th 78.8%	19th 73.2%	9th 77.6%	6th 78.2%	8th 77.7%	11th 77.4%	14th 76.0%	21st 72.1%	10th 77.5%	16th 75.4%	7th 77.9%	5th 78.4%	17th 75.2%	20th 73.0%	18th 74.5%	13th 76.6%	15th 75.9%
76.3%	77%	78%	77%	77%	80%	73%	80%	79%	80%	73%	76%	69%	73%	73%	76%	80%	73%	73%	85%	81%	69%
79.4%	74%	79%	84%	84%	64%	80%	84%	82%	76%	88%	95%	59%	82%	80%	84%	82%	72%	78%	83%	73%	84%
58.8%	57%	57%	55%	59%	63%	63%	71%	57%	55%	57%	63%	71%	63%	63%	57%	57%	57%	57%	39%	57%	57%
81.0%	80%	80%	77%	90%	87%	78%	81%	80%	77%	86%	87%	87%	77%	71%	81%	77%	82%	82%	74%	81%	87%
76.1%	77%	74%	74%	77%	74%	74%	77%	86%	82%	81%	74%	74%	74%	74%	72%	85%	74%	74%	74%	74%	74%
73.9%	71%	71%	65%	71%	68%	88%	72%	86%	77%	72%	72%	77%	72%	76%	66%	72%	77%	74%	76%	77%	72%
80.2%	77%	87%	82%	74%	84%	82%	83%	84%	87%	82%	79%	79%	82%	85%	72%	77%	73%	74%	82%	82%	77%
66.5%	66%	56%	64%	69%	74%	56%	62%	68%	69%	66%	64%	63%	74%	61%	71%	81%	75%	69%	61%	64%	63%
87.8%	89%	88%	88%	88%	94%	67%	87%	91%	90%	91%	87%	87%	95%	86%	83%	90%	90%	86%	79%	94%	94%
84.5%	87%	81%	82%	90%	87%	87%	87%	80%	82%	90%	82%	63%	87%	87%	93%	87%	83%	80%	87%	87%	85%
60.8%	71%	69%	77%	70%	71%	65%	68%	65%	57%	47%	71%	76%	53%	43%	60%	56%	39%	42%	48%	64%	64%
72.8%	85%	78%	71%	75%	81%	62%	78%	81%	71%	73%	72%	81%	64%	65%	72%	76%	68%	57%	70%	68%	81%
74.0%	71%	81%	75%	75%	75%	71%	75%	68%	77%	73%	77%	79%	79%	64%	74%	75%	70%	77%	75%	75%	69%
67.5%	67%	71%	70%	68%	64%	72%	66%	68%	69%	67%	64%	64%	68%	71%	66%	64%	67%	68%	64%	66%	73%
86.3%	87%	87%	87%	84%	85%	81%	90%	87%	88%	87%	90%	90%	90%	77%	88%	81%	83%	94%	83%	85%	89%
82.9%	85%	81%	89%	86%	80%	85%	80%	89%	81%	80%	81%	76%	80%	86%	85%	81%	85%	89%	81%	80%	80%
74.3%	77%	83%	77%	74%	80%	68%	71%	58%	67%	77%	75%	77%	59%	71%	77%	80%	76%	77%	77%	80%	80%
73.8%	76%	78%	81%	76%	70%	75%	75%	76%	77%	81%	70%	66%	73%	77%	76%	74%	71%	66%	70%	71%	71%
68.0%	70%	56%	63%	57%	82%	53%	76%	70%	68%	73%	62%	47%	80%	78%	82%	74%	65%	76%	51%	68%	76%
79.4%	88%	65%	88%	85%	85%	79%	80%	88%	76%	86%	61%	62%	77%	85%	77%	75%	79%	83%	82%	80%	86%
85.7%	88%	85%	89%	94%	85%	86%	91%	90%	85%	90%	91%	85%	88%	91%	82%	82%	82%	66%	77%	82%	90%
88.3%	95%	88%	85%	91%	90%	84%	89%	83%	86%	90%	88%	85%	90%	95%	85%	90%	84%	85%	93%	93%	86%
57.0%	57%	58%	64%	58%	64%	62%	58%	62%	68%	66%	58%	38%	67%	67%	52%	54%	50%	45%	64%	46%	38%
66.1%	69%	59%	67%	71%	64%	67%	72%	68%	69%	73%	64%	64%	69%	64%	62%	64%	64%	61%	69%	64%	64%
77.2%	79%	77%	74%	81%	83%	86%	76%	89%	84%	69%	68%	84%	84%	73%	81%	78%	74%	70%	79%	69%	63%
82.1%	87%	89%	88%	88%	83%	77%	83%	77%	75%	88%	83%	82%	87%	77%	89%	84%	71%	80%	76%	78%	82%
86.9%	94%	77%	94%	91%	91%	91%	89%	88%	88%	90%	70%	80%	88%	91%	84%	89%	89%	87%	82%	91%	80%
79.1%	83%	75%	82%	82%	87%	70%	72%	89%	82%	74%	77%	73%	83%	76%	91%	94%	72%	76%	80%	70%	73%
59.1%	67%	80%	80%	73%	67%	45%	61%	65%	58%	45%	38%	38%	44%	53%	67%	74%	52%	43%	65%	62%	65%
72.4%	76%	72%	83%	78%	79%	57%	69%	77%	73%	62%	77%	69%	77%	66%	72%	70%	75%	74%	77%		66%
84.0%	83%	84%	86%	86%	89%	80%	89%	81%	82%	82%	80%	75%	83%	89%	89%	89%	89%	62%	94%	86%	86%
66.1%	61%	61%	70%	72%	74%	74%	66%	69%	74%	61%	66%	66%	66%	66%	61%	61%	61%	66%	66%		61%
87.2%	93%	93%	93%	93%	91%	66%	71%	85%	85%	93%	91%	78%	91%	91%	93%	91%	93%	91%	66%	91%	93%
71.6%	76%	68%	75%	79%	80%	74%	68%	70%	70%	71%	69%	73%	71%	66%	79%	73%	78%	57%	68%	71%	67%
82.6%	90%	71%	90%	90%	79%	82%	79%	79%	82%	82%	79%	88%	88%	88%	90%	81%	74%	79%	83%	79%	82%
84.2%	90%	84%	90%	90%	68%	71%	79%	90%	89%	80%	93%	72%	90%	81%	80%	90%	91%	79%	79%	94%	89%
80.7%	84%	77%	84%	84%	94%	81%	79%	88%	84%	85%	75%	75%	78%	71%	85%	82%	77%	76%	78%	80%	78%
82.8%	87%	100%	90%	90%	91%	83%	94%	79%	80%	87%	87%	63%	78%	74%	85%	87%	90%	69%	74%	74%	77%
72.1%	76%	76%	76%	76%	75%	71%	74%	77%	77%	74%	75%	58%	73%	67%	71%	76%	68%	68%	65%	71%	71%
92.1%	96%	96%	94%	98%	74%	74%	91%	89%	100%	96%	91%	87%	91%	91%	96%	96%	100%	91%	91%	96%	96%
73.7%	76%	77%	76%	74%	76%	65%	82%	74%	74%	72%	77%	65%	75%	63%	76%	75%	75%	77%	68%	80%	71%
74.2%	79%	83%	75%	80%	65%	52%	75%	75%	71%	75%	76%	65%	75%	79%	83%	75%	83%	76%	75%	71%	71%
89.5%	91%	93%	91%	93%	93%	91%	86%	74%	100%	93%	91%	90%	93%	90%	85%	93%	84%	84%	95%	85%	85%

Model Similarity Dendrogram

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