	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 85.8%	6th 83.7%	9th 83.0%	2nd 84.6%	7th 83.7%	19th 77.7%	11th 82.7%	13th 81.4%	12th 81.9%	10th 82.7%	3rd 84.1%	15th 79.3%	5th 83.7%	14th 80.7%	8th 83.7%	4th 84.0%	17th 78.3%	18th 78.2%	16th 78.9%	20th 77.6%	21st 73.2%
85.4%	95%	85%	75%	92%	82%	66%	84%	82%	79%	84%	89%	83%	89%	82%	90%	89%	85%	93%	89%	90%	91%
88.6%	82%	86%	92%	93%	88%	94%	90%	79%	86%	92%	94%	76%	90%	90%	91%	88%	91%	85%	92%	92%	90%
74.3%	72%	67%	79%	79%	72%	75%	70%	75%	71%	80%	79%	81%	72%	70%	70%	70%	69%	76%	67%	97%	70%
89.6%	93%	86%	92%	91%	94%	85%	90%	94%	95%	92%	92%	91%	93%	88%	92%	92%	85%	84%	84%	80%	89%
88.0%	98%	90%	81%	89%	97%	89%	89%	97%	94%	95%	96%	94%	95%	93%	97%	95%	64%	80%	86%	64%	64%
88.5%	92%	95%	89%	94%	91%	93%	90%	94%	88%	88%	88%	85%	87%	77%	85%	87%	87%	90%	87%	85%	86%
81.4%	84%	81%	82%	85%	83%	75%	80%	83%	88%	74%	87%	82%	74%	78%	75%	75%	89%	92%	85%	84%	74%
81.4%	84%	81%	77%	79%	80%	55%	85%	95%	92%	82%	87%	80%	85%	78%	88%	94%	81%	86%	71%	72%	77%
83.1%	91%	82%	75%	81%	84%	69%	78%	85%	81%	90%	90%	86%	89%	85%	87%	89%	93%	78%	80%	76%	76%
86.6%	91%	95%	86%	86%	84%	95%	90%	86%	79%	89%	85%	92%	91%	89%	75%	90%	69%	76%	90%	87%	94%
78.9%	83%	91%	91%	91%	73%	90%	78%	85%	78%	76%	90%	78%	77%	68%	80%	76%	70%	55%	85%	68%	74%
92.0%	91%	93%	92%	96%	96%	94%	92%	94%	91%	91%	87%	93%	95%	91%	93%	91%	94%	86%	95%	89%	87%
85.4%	86%	92%	83%	86%	86%	86%	91%	80%	88%	90%	92%	72%	96%	95%	95%	94%	85%	73%	85%	86%	53%
82.9%	92%	87%	86%	85%	89%	80%	92%	74%	83%	78%	92%	72%	85%	91%	80%	80%	70%	88%	93%	75%	68%
86.6%	93%	90%	94%	90%	82%	82%	88%	85%	88%	85%	89%	81%	90%	90%	90%	90%	83%	84%	82%	84%	79%
84.9%	94%	87%	91%	89%	92%	65%	84%	86%	76%	88%	81%	81%	86%	72%	87%	96%	86%	93%	83%	79%	86%
67.2%	74%	74%	73%	75%	71%	58%	70%	47%	59%	71%	75%	59%	61%	58%	80%	70%	60%	59%	73%	66%	79%
68.3%	78%	67%	70%	79%	69%	50%	58%	68%	63%	64%	61%	69%	69%	54%	76%	69%	75%	85%	59%	80%	71%
58.5%	61%	50%	73%	66%	62%	47%	63%	56%	57%	59%	57%	53%	57%	56%	83%	65%	55%	51%	44%	63%	50%
84.8%	84%	71%	80%	80%	91%	92%	79%	88%	91%	80%	92%	94%	84%	85%	83%	88%	88%	88%	88%	79%	76%
87.3%	93%	93%	90%	87%	93%	76%	95%	81%	92%	87%	89%	90%	93%	90%	89%	93%	80%	82%	66%	91%	83%
84.6%	87%	89%	83%	82%	93%	83%	88%	88%	86%	84%	89%	81%	88%	88%	93%	92%	88%	80%	76%	77%	62%
78.6%	74%	72%	77%	81%	77%	91%	89%	87%	77%	74%	89%	67%	79%	92%	74%	78%	78%	74%	77%	70%	73%
85.7%	89%	90%	88%	89%	88%	91%	87%	88%	85%	93%	90%	72%	91%	90%	90%	90%	88%	78%	79%		57%
82.2%	83%	81%	84%	81%	87%	86%	90%	72%	81%	80%	95%	71%	86%	90%	81%	83%	68%	88%	89%	83%	67%
76.1%	82%	78%	80%	78%	81%	74%	75%	67%	76%	78%	79%	71%	82%	75%	81%	79%	61%	86%	78%	79%	59%
71.9%	82%	74%	71%	75%	69%	57%	63%	72%	71%	67%	60%	73%	77%	63%	80%	78%	76%	81%	71%	78%	72%
81.4%	87%	91%	81%	86%	89%	63%	82%	91%	91%	85%	82%	90%	86%	67%	93%	89%	74%	78%	65%	68%	71%
76.8%	90%	94%	88%	89%	78%	71%	86%	72%	71%	72%	73%	69%	73%	73%	76%	77%	69%	72%	72%	72%	75%
74.3%	80%	87%	75%	85%	86%	67%	67%	83%	82%	73%	76%	69%	74%	73%	75%	70%	71%	42%	77%	67%	81%
82.2%	89%	83%	90%	82%	89%	81%	82%	79%	81%	83%	90%	76%	84%	88%	86%	92%	82%	75%	79%	80%	56%
74.6%	80%	84%	71%	71%	78%	75%	80%	75%	79%	70%	71%	69%	78%	80%	78%	80%	81%	74%	84%	54%	54%
71.7%	69%	64%	75%	76%	69%	72%	67%	72%	68%	77%	75%	78%	69%	67%	64%	67%	66%	73%	64%	94%	80%
82.6%	89%	83%	80%	91%	87%	74%	82%	90%	90%	91%	87%	83%	79%	68%	86%	93%	92%	73%	68%	73%	76%
77.8%	96%	85%	81%	81%	86%	91%	69%	79%	75%	80%	64%	85%	84%	94%	60%	66%	73%	69%	74%	88%	54%
82.7%	84%	87%	86%	84%	78%	81%	93%	86%	89%	86%	87%	88%	87%	84%	72%	79%	79%	75%	76%	80%	76%
83.2%	88%	87%	88%	83%	84%	89%	87%	72%	87%	87%	90%	81%	89%	89%	82%	86%	77%	68%	90%	84%	59%
87.2%	95%	91%	91%	95%	85%	98%	88%	94%	99%	96%	95%	77%	98%	75%	98%	99%	71%	83%	86%	68%	49%
84.7%	97%	87%	94%	94%	87%	76%	90%	92%	85%	92%	87%	84%	87%	78%	92%	89%	82%	61%	72%	79%	73%
94.4%	95%	96%	91%	91%	98%	95%	100%	94%	98%	89%	91%	88%	98%	100%	97%	100%	99%	93%	96%	73%	100%
84.8%	88%	89%	92%	95%	93%	62%	93%	94%	82%	95%	90%	78%	90%	84%	91%	89%	72%	79%	73%	61%	90%
80.9%	83%	86%	77%	77%	78%	72%	83%	83%	78%	90%	81%	84%	85%	88%	84%	79%	80%	85%	83%	73%	69%
77.2%	71%	78%	76%	79%	79%	76%	79%	55%	70%	81%	82%	83%	78%	83%	78%	77%	79%	92%	78%	70%	78%

Model Similarity Dendrogram

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