	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	2nd 79.9%	5th 78.8%	3rd 79.0%	1st 80.6%	7th 78.4%	21st 67.3%	14th 74.6%	12th 75.9%	13th 75.5%	4th 78.9%	10th 76.4%	17th 73.3%	9th 77.0%	18th 72.4%	8th 77.9%	6th 78.5%	11th 76.1%	20th 71.1%	19th 72.2%	15th 73.9%	16th 73.9%
79.4%	83%	85%	81%	93%	90%	54%	73%	81%	78%	85%	77%	83%	81%	73%	78%	81%	78%	89%	64%	81%	80%
75.3%	71%	68%	74%	79%	44%	94%	71%	78%	63%	78%	88%	91%	84%	93%	72%	61%	79%	62%	87%	79%	66%
70.4%	76%	66%	76%	74%	72%	68%	66%	68%	60%	79%	72%	72%	68%	68%	66%	70%	63%	68%	58%	97%	71%
82.9%	86%	84%	81%	84%	80%	76%	84%	84%	86%	82%	89%	79%	89%	83%	82%	89%	84%	87%	73%	79%	79%
80.4%	82%	85%	80%	89%	80%	80%	80%	80%	80%	88%	94%	82%	94%	78%	85%	80%	82%	78%	79%	53%	60%
79.4%	77%	81%	73%	84%	81%	86%	80%	86%	81%	80%	83%	76%	79%	76%	74%	81%	84%	72%	76%	70%	88%
89.1%	91%	90%	85%	89%	92%	87%	87%	87%	93%	89%	93%	82%	92%	93%	88%	85%	95%	93%	83%	90%	88%
61.3%	67%	61%	66%	75%	63%	34%	61%	64%	56%	75%	55%	55%	63%	51%	73%	65%	58%	66%	54%	57%	69%
77.5%	78%	90%	78%	81%	77%	48%	72%	73%	64%	89%	82%	81%	80%	74%	85%	86%	86%	64%	73%	81%	86%
78.4%	81%	79%	81%	82%	79%	87%	74%	68%	81%	83%	71%	79%	81%	79%	78%	76%	74%	79%	79%	77%	79%
81.9%	90%	91%	91%	90%	81%	80%	87%	78%	85%	72%	87%	84%	86%	82%	78%	86%	75%	70%	76%	78%	73%
79.7%	93%	82%	86%	83%	86%	73%	76%	83%	84%	76%	78%	83%	71%	74%	86%	74%	71%	66%	87%	80%	81%
82.4%	86%	76%	90%	94%	86%	75%	87%	89%	85%	89%	77%	80%	76%	76%	85%	85%	82%	81%	69%	81%	81%
82.0%	91%	82%	82%	82%	86%	79%	86%	87%	90%	80%	85%	81%	85%	66%	77%	79%	77%	78%	82%	88%	78%
86.9%	89%	88%	84%	86%	91%	86%	90%	91%	91%	84%	87%	90%	88%	89%	78%	93%	86%	85%	90%	79%	80%
72.3%	82%	79%	80%	83%	76%	53%	66%	76%	72%	80%	66%	63%	79%	68%	73%	75%	61%	84%	67%	77%	58%
60.0%	72%	74%	74%	63%	60%	46%	60%	50%	61%	61%	65%	42%	60%	55%	66%	56%	60%	53%	55%	61%	67%
65.0%	72%	70%	78%	79%	71%	40%	55%	72%	56%	72%	54%	65%	72%	54%	67%	77%	67%	61%	58%	62%	62%
52.8%	53%	46%	56%	46%	78%	40%	54%	59%	56%	63%	54%	39%	54%	46%	59%	70%	53%	44%	41%	54%	43%
75.9%	84%	80%	81%	80%	70%	71%	76%	71%	72%	81%	73%	70%	82%	70%	86%	85%	72%	66%	78%	70%	75%
83.3%	86%	88%	86%	87%	93%	58%	90%	89%	80%	90%	84%	76%	84%	73%	88%	92%	92%	77%	56%	87%	93%
79.5%	95%	82%	80%	91%	88%	52%	80%	84%	78%	91%	69%	66%	78%	66%	86%	91%	73%	86%	54%	94%	86%
77.0%	75%	86%	82%	80%	82%	83%	79%	73%	80%	80%	81%	37%	70%	82%	82%	79%	81%	75%	82%	77%	72%
80.1%	82%	76%	84%	74%	81%	74%	84%	79%	82%	84%	80%	79%	82%	81%	82%	83%	81%	79%	74%	81%	81%
76.1%	69%	77%	76%	74%	81%	79%	79%	80%	79%	78%	80%	79%	78%	71%	75%	74%	69%	79%	80%	64%	77%
69.4%	76%	70%	76%	70%	75%	58%	66%	72%	73%	73%	68%	72%	69%	67%	70%	73%	64%	56%	70%	68%	71%
82.5%	89%	89%	89%	84%	92%	54%	76%	90%	82%	87%	73%	82%	92%	73%	86%	85%	90%	83%	85%	75%	77%
73.0%	72%	72%	69%	82%	92%	50%	73%	83%	84%	79%	59%	56%	76%	55%	94%	77%	77%	65%	61%		84%
77.6%	85%	87%	89%	100%	81%	67%	79%	69%	76%	74%	71%	71%	72%	69%	89%	81%	73%	69%	72%	75%	80%
73.9%	79%	78%	79%	85%	82%	57%	63%	76%	83%	80%	71%	67%	75%	67%	81%	78%	90%	61%	76%	60%	63%
68.6%	69%	70%	63%	47%	64%	92%	64%	68%	73%	60%	83%	88%	74%	82%	43%	58%	69%	74%	79%	69%	52%
77.4%	69%	80%	69%	71%	73%	78%	80%	78%	86%	66%	73%	73%	78%	78%	80%	78%	82%	86%	88%	80%	80%
69.3%	76%	66%	76%	74%	72%	68%	66%	68%	60%	79%	72%	72%	68%	68%	72%	68%	70%	60%	58%	71%	72%
74.1%	78%	73%	78%	78%	75%	68%	70%	76%	74%	76%	69%	70%	71%	70%	78%	80%	78%	76%	70%	72%	77%
57.3%	58%	74%	57%	83%	58%	56%	46%	39%	52%	54%	54%	59%	50%	49%	70%	76%	55%	42%	73%	56%	43%
75.8%	80%	77%	81%	82%	77%	62%	76%	84%	75%	84%	80%	68%	76%	68%	71%	80%	75%	71%	66%	79%	79%
80.5%	85%	87%	83%	70%	89%	90%	82%	67%	87%	75%	97%	84%	84%	89%	59%	64%	84%	80%	86%	71%	77%
82.1%	71%	86%	84%	97%	79%	73%	80%	80%	82%	81%	94%	83%	84%	88%	94%	94%	87%	75%	91%	54%	68%
71.7%	84%	78%	73%	82%	75%	57%	83%	78%	67%	77%	62%	69%	78%	54%	80%	77%	79%	56%	56%	74%	66%
86.3%	94%	83%	94%	92%	90%	85%	83%	85%	76%	97%	90%	90%	85%	85%	85%	87%	81%	85%	74%	85%	87%
73.6%	80%	79%	77%	77%	74%	59%	80%	80%	76%	87%	77%	71%	72%	72%	80%	76%	72%	28%	72%	75%	81%
80.4%	88%	88%	82%	86%	84%	58%	77%	82%	75%	82%	84%	83%	78%	83%	85%	85%	78%	75%	78%	78%	79%
76.0%	90%	87%	91%	82%	71%	61%	66%	58%	71%	72%	86%	79%	74%	76%	82%	84%	87%	72%	73%	66%	69%

Model Similarity Dendrogram

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