	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 86.2%	8th 81.2%	4th 83.3%	3rd 84.0%	10th 80.7%	20th 75.5%	21st 75.1%	13th 79.9%	9th 81.1%	6th 82.6%	15th 78.7%	18th 77.0%	12th 80.2%	17th 77.1%	2nd 84.1%	5th 82.9%	14th 79.8%	19th 76.0%	16th 78.6%	7th 81.6%	11th 80.4%
81.8%	79%	85%	89%	88%	87%	83%	87%	79%	88%	85%	89%	86%	84%	78%	85%	92%	78%	24%	87%	82%	82%
74.9%	80%	84%	74%	85%	50%	90%	85%	82%	70%	70%	89%	76%	68%	86%	61%	58%	83%	71%	81%	69%	60%
74.9%		82%	94%	80%	82%	61%	10%	70%	68%	82%	82%	86%	82%	86%	82%	82%	82%	61%	61%	82%	82%
85.9%	89%	82%	88%	86%	88%	89%	88%	84%	89%	89%	89%	86%	82%	87%	91%	87%	84%	65%	86%	86%	89%
83.6%	83%	81%	87%	87%	81%	81%	80%	85%	78%	84%	81%	81%	86%	81%	95%	90%	84%	81%	81%	81%	87%
64.5%		72%	71%	79%	77%	65%	62%	66%	66%	65%	59%	61%	63%	65%	69%	69%	52%	69%	61%	46%	53%
83.0%	89%	81%	80%	85%	83%	71%	76%	91%	91%	81%	74%	95%	80%	73%	90%	95%	81%	86%	72%	80%	88%
79.9%	81%	80%	85%	85%	80%	54%	73%	89%	81%	89%	77%	69%	80%	77%	86%	88%	84%	79%	78%	80%	83%
74.3%	86%	63%	73%	76%	76%	45%	66%	74%	68%	82%	67%	68%	77%	50%	89%	86%	95%	89%	61%	76%	93%
84.3%	86%	86%	93%	93%	86%	86%	77%	59%	89%	86%	86%	86%	86%	86%	86%	83%	75%	82%	86%	84%	89%
78.0%		89%	87%	83%	50%	86%	87%	86%	76%	76%	86%	87%	69%	65%	82%	81%	68%	55%	80%	88%	79%
83.9%	93%	90%	89%	90%	91%	67%	75%	89%	84%	90%	73%	91%	89%	87%	87%	79%	72%	66%	85%		91%
90.3%	92%	90%	92%	91%	87%	92%	94%	96%	96%	90%	93%	74%	90%	93%	89%	91%	90%	85%	97%	94%	81%
85.8%	92%	85%	86%	88%	88%	85%	73%	83%	86%	90%	87%	73%	93%	93%	91%	89%	72%	92%	86%	83%	87%
92.0%	93%	94%	93%	93%	92%	90%	95%	93%	96%	92%	93%	89%	94%	85%	88%	95%	88%	93%	97%	91%	89%
94.2%	95%	93%	98%	97%	96%	95%	96%	96%	96%	95%	89%	91%	96%	91%	95%	91%	95%	91%	96%	96%	90%
78.2%		86%	87%	87%	88%	77%	61%	55%	85%	86%	71%	65%	70%	63%	75%	87%	83%	88%	83%		88%
83.7%	87%	78%	84%	85%	80%	85%	83%	89%	88%	83%	76%	71%	85%	82%	84%	80%	89%	82%	86%	96%	84%
71.9%	69%	63%	65%	61%	78%	60%	87%	74%	75%	81%	73%	65%	72%	66%	79%	83%	76%	70%	56%	90%	67%
85.7%	92%	83%	92%	92%	88%	88%	90%	85%	86%	86%	78%	82%	83%	87%	92%	87%	84%	76%	90%	82%	77%
85.5%	94%	88%	90%	95%	78%	68%	81%	74%	77%	95%	75%	82%	91%	88%	98%	92%	88%	94%	76%	78%	93%
87.4%	91%	90%	90%	92%	77%	85%	86%	85%	82%	90%	78%	82%	89%	92%	91%	92%	85%	91%	81%	94%	92%
77.0%	77%	69%	69%	72%	85%	79%	84%	84%	85%	84%	84%	59%	78%	89%	77%	82%	72%	72%	73%	69%	74%
88.4%	91%	72%	91%	89%	93%	84%	93%	88%	88%	93%	88%	93%	93%	93%	89%	93%	91%	77%	84%	93%	81%
86.2%	82%	88%	91%	88%	93%	86%	89%	84%	91%	88%	88%	86%	84%	84%	85%	90%	90%	80%	83%	86%	75%
76.0%	77%	89%	74%	73%	72%	64%	77%	71%	69%	74%	81%	83%	72%	66%	84%	76%	67%	67%	88%	88%	83%
78.2%	88%	67%	84%	87%	90%	76%	79%	82%	75%	79%	61%	66%	78%	77%	88%	82%	88%	66%	75%	71%	84%
80.0%	86%	80%	84%	84%	86%	60%	83%	86%	89%	84%	72%	73%	75%	60%	89%	86%	79%	92%	71%	83%	78%
72.8%	84%	85%	86%	85%	82%	77%	77%	62%	66%	67%	59%	59%	62%	59%	84%	77%	69%	59%	72%	69%	89%
75.6%	86%	73%	73%	82%	77%	70%	74%	80%	74%	74%	72%	76%	70%	70%	76%	77%	74%	80%	79%	76%	75%
86.3%	87%	87%	88%	84%	87%	84%	87%	83%	86%	83%	85%	87%	86%	87%	88%	89%	89%	82%	87%	89%
64.6%		64%	70%	60%	77%	61%	49%	66%	77%	64%	70%	49%	64%	49%	64%	64%	64%	77%	61%	77%	64%
66.2%		67%	59%	67%	86%	86%	10%	58%	56%	67%	69%	69%	69%	86%	67%	67%	67%	69%	69%	69%	67%
84.8%	86%	75%	86%	91%	83%	88%	79%	89%	82%	83%	83%	82%	83%	82%	87%	87%	90%	88%	80%	87%	90%
69.4%	97%	86%	85%	91%	67%	42%	59%	61%	66%	64%	51%	78%	71%	51%	83%	71%	79%	38%	71%	64%	82%
77.8%	83%	75%	88%	86%	84%	63%	75%	88%	78%	84%	79%	71%	81%	74%	79%	79%	73%	71%	67%	84%	71%
90.7%	95%	94%	95%	94%	90%	85%	93%	90%	93%	90%	93%	87%	93%	87%	94%	90%	87%	87%	90%	90%	87%
87.9%	96%	94%	93%	86%	74%	97%	86%	84%	99%	99%	87%	81%	84%	81%	92%	91%	82%	86%	81%	94%	79%
84.5%	93%	93%	89%	92%	73%	78%	94%	88%	88%	83%	86%	73%	87%	81%	83%	80%	75%	83%	88%	89%	78%
80.2%		95%	77%	77%	77%	77%	10%	93%	85%	95%	77%	69%	82%	69%	95%	95%	95%	82%	82%	77%	95%
69.2%	69%	62%	63%	64%	78%	58%	67%	86%	84%	73%	78%	54%	75%	54%	75%	70%	76%	69%	56%	78%	65%
65.8%	68%	63%	59%	69%	66%	52%	78%	70%	65%	75%	61%	78%	64%	73%	65%	65%	58%	63%	68%	65%	57%
82.5%		90%	91%	91%	65%	77%	74%	58%	77%	81%	94%	94%	90%	82%	89%	76%	79%	88%	86%	88%	80%

Model Similarity Dendrogram

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