	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	3rd 84.6%	7th 82.2%	2nd 85.1%	1st 85.2%	15th 80.0%	21st 77.1%	10th 81.7%	13th 80.9%	9th 81.7%	6th 83.1%	12th 81.2%	20th 77.3%	11th 81.6%	19th 79.2%	4th 83.9%	5th 83.5%	18th 79.4%	17th 79.4%	16th 79.7%	8th 81.7%	14th 80.7%
86.6%	85%	87%	88%	89%	87%	92%	87%	87%	85%	86%	92%	79%	86%	86%	88%	90%	83%	81%	87%	88%	86%
73.9%	72%	80%	69%	72%	46%	88%	80%	74%	68%	68%	73%	71%	70%	92%	74%	75%	79%	86%	77%	74%	64%
81.2%	77%	77%	96%	88%	83%	83%	92%	66%	64%	77%	83%	92%	83%	92%	77%	77%	77%	83%	83%	78%	77%
88.5%	92%	82%	92%	86%	90%	77%	94%	93%	95%	90%	93%	87%	93%	82%	95%	95%	83%	88%	82%	87%	82%
85.0%	83%	81%	82%	90%	81%	81%	84%	93%	83%	92%	81%	81%	81%	81%	99%	95%	78%	84%	81%	81%	94%
79.6%	88%	83%	85%	85%	83%	86%	79%	85%	81%	77%	73%	80%	77%	74%	78%	80%	71%	75%	76%	75%	80%
83.3%	90%	88%	86%	91%	90%	76%	82%	92%	84%	84%	78%	81%	78%	77%	82%	90%	87%	77%	79%	81%	77%
71.0%	82%	70%	76%	76%	72%	59%	69%	76%	66%	78%	70%	69%	70%	61%	79%	75%	74%	63%	66%	69%	72%
74.6%	77%	66%	76%	72%	51%	66%	75%	80%	85%	82%	83%	67%	81%	69%	78%	75%	77%	84%	74%	72%	77%
85.1%	87%	87%	87%	94%	87%	87%	81%	67%	78%	92%	82%	87%	94%	87%	87%	89%	83%	64%	87%	87%	94%
80.5%	92%	89%	90%	85%	81%	93%	79%	90%	78%	82%	83%	90%	76%	60%	82%	80%	65%	61%	89%	86%	59%
86.7%	93%	94%	90%	97%	92%	80%	88%	90%	91%	83%	94%	96%	83%	82%	83%	78%	78%	73%	85%	78%	92%
86.6%	87%	86%	87%	88%	90%	80%	86%	91%	88%	85%	88%	88%	85%	88%	88%	87%	82%	90%	88%	87%	79%
90.1%	87%	91%	91%	91%	93%	85%	90%	94%	94%	91%	93%	72%	90%	93%	92%	93%	93%	89%	92%	93%	85%
94.4%	97%	97%	93%	93%	96%	94%	96%	96%	93%	96%	96%	94%	97%	95%	91%	90%	91%	92%	95%	94%	97%
91.1%	96%	93%	95%	93%	95%	86%	90%	95%	90%	87%	90%	85%	89%	93%	87%	90%	93%	92%	92%		90%
75.4%	69%	86%	94%	86%	72%	71%	68%	48%	71%	80%	73%	70%	57%	70%	79%	82%	83%	75%	77%	92%	80%
81.8%	88%	77%	82%	81%	85%	75%	78%	82%	84%	80%	82%	77%	82%	80%	83%	80%	85%	85%	82%	90%	80%
63.6%	62%	53%	62%	52%	66%	41%	65%	61%	69%	72%	57%	47%	76%	74%	75%	84%	53%	61%	45%	72%	88%
82.0%	85%	71%	86%	86%	84%	80%	89%	86%	89%	86%	68%	68%	87%	81%	88%	79%	80%	82%	89%	83%	76%
89.4%	86%	89%	91%	91%	90%	89%	89%	88%	94%	89%	92%	90%	94%	96%	86%	93%	85%	91%	86%	81%	88%
90.4%	92%	91%	91%	90%	91%	85%	90%	95%	93%	86%	85%	90%	94%	91%	89%	89%	92%	87%	93%	90%	94%
74.1%	75%	83%	81%	76%	80%	81%	81%	77%	72%	79%	83%	59%	65%	78%	69%	66%	68%	72%	82%	61%	69%
87.5%	91%	78%	90%	93%	88%	92%	91%	87%	86%	92%	91%	88%	92%	88%	86%	88%	88%	87%	89%	88%	65%
87.1%	89%	89%	86%	91%	88%	94%	87%	88%	88%	90%	90%	73%	92%	89%	88%	90%	87%	74%	85%	91%	80%
79.6%	81%	85%	80%	84%	85%	77%	78%	73%	74%	77%	87%	82%	75%	76%	80%	85%	73%	81%	85%	79%	75%
85.9%	92%	77%	91%	91%	88%	85%	90%	87%	88%	92%	75%	77%	94%	89%	90%	86%	84%	85%	85%	69%	88%
77.3%	78%	79%	81%	79%	83%	60%	77%	85%	87%	79%	76%	72%	73%	59%	89%	81%	84%	83%	66%	75%	78%
72.3%	82%	89%	85%	86%	83%	74%	59%	76%	73%	64%	59%	59%	60%	59%	77%	82%	65%	61%	67%	83%	75%
78.2%	93%	80%	88%	88%	84%	53%	75%	85%	83%	79%	72%	69%	69%	69%	85%	84%	80%	75%	75%	72%	84%
92.7%	94%	95%	95%	95%	92%	95%	95%	93%	94%	93%	91%	92%	93%	92%	93%	94%	89%	82%	94%	93%	93%
55.5%	54%	54%	53%	53%	66%	43%	54%	57%	66%	54%	66%	43%	54%	50%	54%	54%	54%	66%	50%	66%	54%
72.1%	68%	68%	83%	81%	75%	75%	92%	61%	61%	68%	75%	75%	75%	92%	68%	68%	68%	75%	43%	75%	68%
82.1%	91%	82%	83%	90%	70%	76%	78%	89%	83%	84%	79%	89%	81%	70%	82%	86%	84%	91%	74%	80%	83%
66.5%	81%	83%	81%	86%	36%	63%	60%	60%	56%	61%	55%	69%	62%	58%	68%	62%	66%	62%	81%		81%
82.4%	88%	80%	87%	90%	67%	72%	87%	85%	89%	92%	89%	71%	89%	72%	88%	85%	75%	79%	74%	88%	84%
93.4%	94%	95%	94%	93%	90%	94%	93%	85%	96%	90%	96%	92%	97%	94%	95%	91%	93%	93%	96%	96%	95%
87.9%	84%	92%	96%	91%	85%	81%	93%	92%	93%	99%	93%	81%	88%	81%	93%	94%	72%	79%	81%	93%	85%
81.2%	90%	81%	85%	86%	79%	74%	85%	75%	80%	89%	85%	72%	90%	71%	91%	83%	77%	77%	79%	74%	82%
85.0%	99%	83%	83%	86%	75%	66%	75%	84%	85%	99%	66%	83%	83%	83%	99%	99%	99%	89%	83%	66%	99%
76.3%	82%	72%	77%	78%	88%	57%	73%	80%	86%	82%	89%	64%	83%	67%	84%	83%	68%	75%	60%	90%	64%
73.8%	79%	80%	76%	79%	67%	58%	82%	72%	72%	81%	73%	62%	78%	79%	77%	72%	71%	70%	78%	79%	65%
87.8%	86%	93%	96%	93%	67%	91%	75%	58%	77%	88%	93%	93%	91%	87%	90%	93%	97%	96%	94%	94%	91%

Model Similarity Dendrogram

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