	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 86.0%	3rd 84.9%	4th 84.8%	17th 78.8%	12th 81.5%	16th 79.5%	11th 82.4%	9th 82.6%	10th 82.4%	5th 84.1%	7th 83.4%	14th 80.0%	8th 83.3%	15th 79.9%	2nd 85.9%	6th 83.9%	19th 78.5%	21st 74.6%	13th 80.7%	18th 78.6%	20th 75.1%
87.7%	94%	95%	83%	86%	93%	74%	85%	84%	83%	86%	89%	87%	94%	86%	95%	90%	93%	81%	96%	83%	84%
85.0%	79%	86%	92%	90%	72%	92%	76%	81%	77%	89%	91%	94%	87%	89%	93%	84%	79%	68%	96%	77%	92%
62.7%	63%	62%	59%	0%	59%	74%	67%	67%	59%	74%	74%	71%	74%	69%	65%	62%	66%	59%	58%	67%	67%
89.6%	93%	85%	95%	94%	93%	88%	94%	89%	91%	93%	91%	93%	94%	87%	86%	79%	89%	82%	90%	87%	89%
88.3%	83%	89%	84%	89%	83%	87%	85%	87%	87%	86%	99%	94%	87%	91%	90%	93%	89%	91%	85%	86%	89%
88.7%	88%	92%	88%	92%	95%	91%	89%	95%	87%	86%	92%	90%	82%	77%	86%	84%	91%	95%	86%	84%	92%
91.3%	90%	92%	92%	91%	86%	93%	89%	92%	95%	91%	91%	96%	92%	97%	95%	95%	84%	97%	91%	94%	75%
81.3%	84%	88%	80%	80%	82%	58%	79%	94%	94%	81%	72%	83%	86%	77%	96%	88%	74%	84%	66%	85%	76%
80.7%	81%	79%	78%	79%	75%	67%	80%	81%	84%	90%	87%	86%	83%	82%	87%	86%	84%	71%	77%	79%	79%
89.1%	90%	89%	88%	89%	93%	93%	81%	87%	93%	90%	81%	93%	92%	93%	86%	86%	85%	81%	93%	93%	96%
81.2%	91%	90%	90%	91%	79%	92%	90%	87%	85%	82%	85%	95%	72%	73%	89%	78%	69%	63%	84%	69%	52%
86.7%	93%	92%	91%	98%	85%	94%	83%	92%	87%	74%	88%	93%	74%	83%	83%	86%	82%	76%	91%	85%	90%
83.6%	82%	95%	95%	92%	83%	90%	83%	80%	79%	92%	93%	76%	82%	93%	84%	77%	72%	78%	86%	72%	72%
87.8%	89%	92%	86%	94%	85%	79%	94%	90%	91%	91%	95%	76%	96%	76%	94%	96%	89%	93%	94%	79%	65%
87.8%	93%	94%	95%	92%	92%	84%	95%	84%	89%	93%	94%	82%	96%	89%	91%	96%	84%	71%	86%	87%	56%
82.2%	87%	86%	88%	87%	82%	82%	83%	88%	85%	81%	78%	82%	80%	78%	92%	86%	83%	75%	82%	73%	69%
64.9%		73%	72%	73%	61%	67%	69%	49%	67%	65%	61%	50%	60%	56%	75%	71%	60%	60%	68%	67%	73%
70.8%	76%	73%	78%	84%	65%	51%	61%	80%	75%	65%	63%	72%	77%	60%	75%	75%	77%	68%	73%	69%	69%
69.2%	74%	58%	81%	64%	80%	50%	69%	73%	78%	83%	69%	49%	72%	69%	86%	86%	67%	59%	52%	68%	66%
87.8%	90%	86%	92%	95%	94%	82%	98%	84%	81%	97%	83%	82%	89%	80%	94%	93%	82%	83%	81%		89%
87.0%	97%	91%	88%	89%	93%	74%	92%	89%	92%	92%	90%	87%	94%	86%	91%	85%	71%	85%	81%	90%	70%
84.3%	88%	90%	86%	83%	87%	78%	88%	88%	89%	84%	88%	90%	92%	89%	88%	89%	73%	81%	78%	82%	60%
81.1%	79%	82%	82%	82%	84%	88%	88%	93%	80%	90%	82%	51%	82%	79%	81%	80%	79%	75%	84%	80%	82%
86.2%	92%	92%	90%	91%	90%	91%	85%	87%	87%	96%	93%	75%	88%	88%	97%	89%	79%	62%	81%	79%	79%
87.9%	92%	92%	95%	94%	94%	82%	93%	88%	94%	92%	89%	75%	91%	69%	84%	92%	95%	76%	95%	90%	73%
74.9%	78%	77%	78%	77%	78%	77%	72%	71%	75%	84%	82%	77%	76%	76%	77%	76%	70%	67%	79%	71%	54%
74.6%	82%	78%	76%	78%	75%	65%	73%	78%	78%	74%	63%	78%	79%	67%	82%	78%	76%	78%	79%	65%	65%
85.8%	96%	95%	85%	93%	82%	67%	85%	94%	92%	88%	87%	78%	87%	73%	95%	92%	90%	74%	70%	88%	90%
76.9%	84%	93%	86%	87%	75%	76%	76%	74%	71%	75%	75%	79%	73%	71%	82%	75%	71%	71%	72%	72%	76%
77.5%	80%	86%	80%	82%	95%	81%	64%	88%	81%	74%	76%	68%	76%	72%	77%	81%	79%	67%	84%	69%	67%
84.7%	91%	82%	80%	92%	84%	87%	84%	79%	82%	88%	91%	92%	87%	92%	88%	90%	69%	82%	84%	83%	71%
73.8%	72%	81%	85%	0%	85%	69%	77%	76%	85%	70%	69%	72%	70%	74%	81%	81%	78%	85%	86%	77%	77%
58.9%	67%	58%	55%	0%	55%	70%	63%	63%	55%	69%	69%	67%	69%	65%	59%	58%	61%	55%	54%	62%	62%
84.2%	91%	82%	89%	90%	86%	75%	81%	84%	85%	88%	83%	79%	83%	79%	89%	85%	86%	85%	77%	82%	89%
71.3%	78%	84%	79%	79%	48%	75%	62%	60%	63%	61%	63%	65%	68%	67%	81%	73%	72%	67%	93%		87%
81.6%	85%	84%	91%	86%	75%	87%	89%	84%	80%	87%	88%	80%	86%	80%	86%	86%	83%	64%	72%	85%	56%
83.6%	91%	79%	84%	84%	92%	93%	87%	78%	83%	90%	90%	77%	91%	93%	85%	84%	70%	67%	81%	81%	75%
84.1%	95%	88%	96%	95%	83%	96%	90%	92%	92%	93%	87%	74%	95%	79%	95%	94%	69%	67%	91%	48%	48%
86.8%	96%	93%	96%	96%	90%	79%	93%	88%	88%	93%	91%	90%	90%	78%	91%	88%	67%	85%	69%	84%	77%
90.4%	98%	96%	93%	0%	93%	91%	99%	99%	93%	92%	91%	94%	92%	97%	99%	96%	100%	93%	91%	99%	93%
87.7%	98%	93%	95%	96%	87%	81%	93%	94%	89%	97%	97%	84%	90%	88%	93%	93%	95%	30%	77%	87%	84%
76.9%	79%	80%	74%	75%	73%	67%	81%	76%	75%	79%	76%	83%	81%	87%	74%	72%	76%	72%	76%	74%	85%
76.0%	81%	78%	76%	78%	65%	83%	80%	66%	69%	72%	91%	79%	71%	82%	75%	81%	66%	85%	79%	71%	69%

Model Similarity Dendrogram

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