	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	1st 85.5%	3rd 84.7%	20th 78.1%	19th 78.9%	13th 80.9%	17th 79.7%	8th 82.5%	9th 82.4%	10th 82.1%	6th 83.9%	5th 84.0%	16th 79.7%	7th 83.6%	14th 80.7%	2nd 85.0%	4th 84.3%	18th 78.9%	21st 76.3%	15th 80.1%	11th 81.5%	12th 81.0%
87.5%	96%	94%	82%	86%	81%	73%	86%	96%	90%	85%	89%	87%	95%	88%	86%	87%	87%	89%	95%	83%	83%
86.4%	82%	86%	92%	90%	79%	94%	76%	82%	79%	90%	93%	90%	88%	97%	91%	88%	80%	86%	83%		82%
61.0%	71%	66%	0%	0%	59%	74%	63%	71%	59%	69%	74%	71%	69%	71%	67%	71%	68%	69%	58%	64%	67%
89.8%	93%	85%	95%	92%	93%	86%	94%	89%	91%	93%	91%	93%	95%	83%	89%	91%	83%	78%	89%	92%	91%
87.7%	89%	89%	86%	89%	86%	88%	85%	88%	87%	90%	99%	95%	90%	98%	95%	83%	93%	74%	85%	81%	72%
87.2%	88%	92%	88%	92%	95%	91%	89%	92%	87%	82%	87%	84%	79%	84%	84%	81%	88%	87%	82%	84%	96%
91.1%	89%	92%	92%	91%	75%	93%	89%	93%	95%	91%	92%	91%	90%	97%	93%	95%	95%	93%	84%	96%	87%
81.2%	82%	88%	77%	79%	79%	58%	79%	88%	90%	83%	77%	87%	82%	78%	87%	90%	88%	76%	73%	76%	89%
81.3%	82%	79%	78%	79%	73%	70%	80%	77%	83%	87%	89%	87%	86%	79%	87%	80%	93%	85%	73%	78%	82%
89.3%	89%	90%	89%	89%	93%	96%	90%	83%	86%	89%	85%	93%	89%	93%	91%	84%	90%	74%	93%	98%	91%
83.4%	91%	90%	92%	91%	81%	92%	89%	87%	85%	78%	85%	95%	75%	73%	82%	81%	62%	62%	85%	87%	88%
86.8%	94%	93%	92%	97%	89%	94%	83%	91%	87%	72%	89%	93%	80%	83%	84%	76%	82%	76%	95%	85%	87%
83.1%	86%	95%	95%	92%	80%	90%	82%	78%	84%	96%	93%	76%	84%	90%	90%	82%	58%	64%	87%	72%	72%
89.9%	86%	92%	94%	93%	96%	79%	92%	90%	92%	90%	90%	76%	97%	76%	96%	94%	85%	91%	92%	92%	95%
89.0%	91%	94%	95%	92%	84%	84%	95%	90%	87%	90%	95%	82%	95%	90%	95%	92%	81%	71%	86%	90%	91%
83.0%	88%	84%	91%	90%	86%	82%	83%	86%	84%	79%	80%	82%	85%	77%	87%	87%	70%	75%	84%		81%
65.8%	74%	73%	72%	73%	61%	67%	69%	49%	67%	65%	61%	56%	58%	56%	69%	75%	67%	58%	68%	77%	67%
71.9%	80%	70%	70%	84%	67%	54%	61%	73%	72%	67%	61%	73%	75%	61%	78%	75%	83%	81%	76%	78%	70%
70.6%	80%	57%	81%	67%	92%	51%	69%	68%	78%	85%	78%	48%	78%	69%	82%	80%	62%	57%	58%	82%	60%
87.9%	94%	86%	92%	95%	93%	82%	98%	85%	81%	95%	85%	79%	95%	83%	96%	95%	81%	83%	81%	79%	87%
87.5%	92%	91%	88%	87%	92%	74%	95%	81%	95%	92%	93%	87%	93%	89%	87%	82%	81%	82%	72%	91%	93%
85.2%	87%	90%	86%	83%	82%	78%	92%	88%	88%	87%	86%	89%	87%	89%	88%	93%	83%	78%	80%	81%	74%
82.4%	85%	82%	82%	82%	90%	88%	88%	89%	77%	91%	92%	72%	85%	79%	85%	82%	78%	70%	86%	78%	70%
87.0%	93%	92%	90%	93%	90%	91%	84%	87%	87%	94%	91%	75%	88%	94%	90%	91%	79%	78%	81%	79%	79%
87.6%	92%	92%	95%	95%	88%	82%	92%	89%	94%	94%	94%	65%	90%	75%	84%	85%	90%	90%	88%	90%	76%
75.0%	78%	77%	78%	77%	79%	77%	72%	69%	74%	78%	82%	77%	74%	85%	72%	78%	69%	54%	77%	74%	74%
74.1%	78%	75%	76%	78%	75%	65%	74%	81%	75%	74%	62%	74%	80%	67%	77%	81%	75%	73%	71%	65%	80%
86.3%	92%	96%	85%	94%	95%	64%	90%	93%	92%	90%	89%	78%	87%	71%	95%	95%	85%	73%	70%	85%	93%
76.9%	84%	90%	86%	87%	79%	76%	76%	74%	71%	75%	75%	71%	72%	66%	81%	76%	73%	79%	70%	77%	76%
78.1%	76%	86%	80%	83%	79%	81%	64%	88%	82%	74%	76%	64%	73%	72%	83%	80%	78%	94%	77%	82%	68%
84.5%	92%	82%	80%	92%	80%	87%	84%	79%	82%	84%	88%	91%	87%	94%	84%	90%	71%	71%	83%	83%	91%
69.8%	74%	78%	0%	0%	85%	69%	81%	72%	85%	74%	69%	72%	74%	72%	76%	72%	76%	74%	86%	99%	77%
57.0%	67%	61%	0%	0%	55%	70%	55%	70%	55%	65%	69%	67%	65%	67%	62%	67%	63%	65%	54%	59%	62%
83.9%	92%	82%	89%	91%	78%	77%	81%	84%	84%	90%	84%	79%	82%	78%	85%	88%	90%	85%	76%	83%	84%
71.7%	72%	84%	79%	79%	41%	75%	62%	71%	62%	61%	63%	66%	66%	69%	81%	78%	76%	69%	94%	83%	74%
81.8%	85%	82%	90%	86%	66%	83%	86%	87%	80%	87%	85%	82%	87%	81%	78%	86%	77%	73%	73%		83%
83.6%	89%	79%	84%	84%	91%	90%	87%	78%	83%	89%	91%	80%	90%	92%	79%	81%	71%	66%	90%	86%	75%
87.0%	90%	88%	96%	96%	90%	96%	90%	88%	91%	93%	88%	72%	95%	84%	95%	92%	69%	63%	91%	72%	88%
86.6%	91%	90%	96%	96%	91%	76%	93%	90%	86%	96%	86%	90%	90%	72%	93%	97%	80%	67%	73%	80%	85%
86.4%	100%	100%	0%	0%	93%	91%	97%	95%	93%	97%	91%	94%	96%	94%	99%	94%	98%	96%	91%	97%	99%
89.9%	94%	93%	95%	96%	88%	88%	92%	97%	84%	98%	96%	82%	94%	84%	96%	89%	88%	84%	79%	82%	88%
77.6%	75%	80%	74%	75%	74%	67%	81%	81%	75%	79%	76%	83%	85%	87%	78%	80%	76%	76%	76%	73%	79%
75.4%	72%	78%	76%	79%	56%	82%	80%	57%	70%	70%	91%	79%	68%	82%	78%	81%	72%	91%	79%	68%	75%

Model Similarity Dendrogram

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