	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	1st 82.7%	3rd 82.3%	7th 81.1%	2nd 82.6%	13th 79.1%	20th 74.6%	11th 79.7%	5th 81.9%	8th 80.7%	14th 78.7%	9th 80.4%	10th 80.2%	12th 79.7%	18th 77.0%	6th 81.5%	4th 82.2%	15th 77.9%	19th 75.7%	17th 77.5%	21st 74.2%	16th 77.7%
81.0%	83%	78%	72%	77%	86%	67%	76%	80%	81%	78%	87%	93%	85%	82%	80%	83%	85%	80%	86%	82%	81%
75.0%	72%	78%	68%	69%	89%	91%	72%	77%	65%	70%	73%	88%	73%	90%	78%	73%	71%	60%	91%	66%	61%
72.0%	71%	72%	84%	78%	65%	79%	76%	74%	69%	76%	70%	70%	67%	70%	71%	71%	70%	74%	67%	67%	70%
84.8%	92%	90%	91%	88%	62%	79%	84%	88%	86%	87%	84%	89%	90%	88%	88%	91%	82%	89%	81%	73%	79%
91.0%	93%	97%	79%	91%	89%	82%	89%	88%	89%	91%	93%	92%	97%	97%	97%	97%	97%	97%	89%	92%	76%
85.7%	87%	89%	81%	89%	96%	87%	87%	93%	86%	84%	86%	83%	84%	76%	82%	85%	84%	88%	76%	78%	98%
83.5%	90%	82%	84%	92%	84%	79%	85%	88%	92%	76%	79%	90%	82%	76%	79%	89%	79%	92%	83%	75%	78%
74.0%	78%	68%	70%	70%	69%	50%	75%	89%	84%	75%	72%	80%	71%	63%	87%	79%	77%	83%	65%	74%	74%
75.5%	76%	70%	65%	70%	81%	59%	69%	70%	69%	73%	77%	81%	73%	74%	75%	79%	93%	79%	70%	86%	97%
88.0%	89%	93%	85%	91%	93%	96%	84%	81%	89%	87%	89%	89%	89%	89%	83%	86%	75%	91%	94%	84%	91%
81.7%	87%	90%	93%	91%	67%	90%	88%	91%	85%	73%	94%	90%	72%	75%	79%	78%	63%	54%	90%	81%	84%
84.1%	90%	82%	90%	88%	71%	87%	81%	92%	81%	82%	84%	85%	84%	84%	84%	82%	83%	84%	87%	74%	92%
87.0%	93%	92%	87%	91%	88%	85%	89%	91%	88%	90%	89%	88%	90%	90%	92%	92%	82%	78%	85%	59%	87%
82.2%	88%	86%	85%	81%	84%	82%	86%	82%	84%	77%	86%	90%	83%	86%	79%	80%	72%	68%	93%	85%	70%
83.7%	78%	87%	90%	87%	80%	83%	86%	85%	85%	81%	90%	83%	86%	87%	84%	88%	86%	68%	81%	83%	79%
74.1%	82%	77%	71%	78%	78%	54%	72%	77%	77%	68%	70%	77%	76%	66%	84%	77%	70%	81%	68%	81%	72%
64.2%	73%	74%	82%	75%	61%	57%	69%	59%	65%	60%	61%	58%	45%	57%	69%	81%	53%	59%	65%	56%	69%
64.3%	71%	64%	63%	68%	67%	42%	57%	74%	66%	61%	57%	62%	70%	51%	70%	73%	74%	57%	62%	70%	71%
61.1%	71%	50%	73%	69%	70%	51%	62%	57%	56%	70%	59%	56%	65%	63%	74%	75%	63%	44%	48%	54%	54%
84.7%	85%	76%	77%	86%	92%	91%	84%	89%	93%	86%	85%	92%	88%	81%	81%	86%	77%	84%	84%	79%	82%
84.8%	88%	88%	86%	84%	88%	73%	93%	84%	92%	83%	82%	89%	87%	79%	90%	85%	92%	78%	73%	90%	77%
83.0%	85%	86%	88%	83%	89%	69%	84%	86%	88%	83%	81%	87%	86%	87%	85%	86%	86%	81%	73%		67%
76.9%	76%	78%	74%	78%	84%	75%	80%	79%	80%	73%	80%	67%	77%	82%	78%	79%	71%	77%	78%	77%	71%
84.1%	87%	88%	87%	87%	89%	78%	81%	88%	91%	88%	90%	72%	88%	95%	81%	86%	89%	76%	78%	58%	90%
77.7%	82%	87%	87%	78%	83%	79%	83%	80%	79%	69%	85%	88%	75%	85%	79%	74%	64%	65%	88%	55%	67%
72.7%	75%	75%	71%	72%	75%	71%	68%	62%	65%	79%	76%	80%	74%	74%	69%	75%	84%	75%	78%	60%	68%
72.8%	84%	75%	72%	83%	72%	49%	70%	78%	73%	74%	65%	77%	77%	60%	76%	80%	73%	75%	71%	68%	77%
77.6%	90%	83%	79%	82%	79%	62%	81%	93%	89%	76%	73%	76%	73%	65%	87%	83%	67%	75%	68%	75%	74%
74.1%	78%	88%	87%	88%	68%	70%	72%	75%	74%	65%	69%	67%	66%	70%	78%	70%	70%	70%	74%	67%	90%
72.3%	78%	80%	74%	78%	70%	63%	60%	82%	73%	68%	73%	70%	78%	64%	72%	78%	73%	70%	78%	70%	66%
88.8%	92%	86%	93%	89%	93%	90%	79%	80%	83%	85%	92%	89%	91%	89%	91%	94%	89%	96%	83%	87%	94%
87.1%	89%	88%	75%	82%	95%	81%	84%	86%	91%	84%	91%	91%	93%	91%	91%	89%	91%	86%	93%	68%	91%
60.2%	60%	61%	72%	66%	54%	67%	64%	63%	58%	64%	58%	58%	56%	58%	58%	60%	58%	58%	56%	58%	58%
84.1%	87%	89%	86%	88%	75%	82%	86%	91%	85%	88%	80%	89%	83%	62%	92%	81%	90%	83%	74%	84%	92%
68.9%	74%	78%	64%	78%	50%	76%	69%	67%	72%	79%	72%	77%	72%	77%	60%	58%	66%	66%	75%	70%	47%
79.9%	86%	90%	91%	88%	68%	68%	90%	88%	83%	90%	83%	76%	79%	68%	71%	86%	75%	72%	67%	79%	80%
84.9%	84%	90%	87%	87%	76%	80%	91%	84%	90%	83%	87%	87%	89%	81%	86%	89%	89%	79%	83%	87%	73%
88.9%	92%	95%	95%	99%	93%	97%	94%	97%	95%	91%	90%	68%	93%	81%	98%	98%	71%	88%	85%	61%	85%
83.8%	93%	87%	94%	92%	86%	67%	91%	92%	84%	81%	88%	83%	86%	69%	92%	89%	86%	78%	69%	84%	69%
92.6%	91%	93%	94%	99%	87%	100%	97%	96%	90%	97%	91%	91%	88%	91%	91%	93%	91%	95%	89%	89%	91%
80.6%	89%	86%	87%	88%	96%	63%	95%	91%	91%	87%	90%	60%	77%	60%	93%	91%	80%	39%	69%	75%	86%
85.3%	84%	93%	77%	84%	82%	74%	78%	91%	82%	81%	87%	90%	97%	96%	93%	86%	83%	83%	84%	80%	86%
75.5%	62%	81%	77%	71%	78%	81%	67%	62%	70%	73%	88%	80%	70%	84%	76%	80%	75%	78%	81%	75%	76%

Model Similarity Dendrogram

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