	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 83.6%	2nd 82.5%	10th 80.9%	4th 82.2%	3rd 82.3%	21st 76.1%	9th 81.0%	12th 80.5%	13th 80.3%	14th 80.0%	7th 81.6%	18th 76.9%	5th 82.2%	16th 79.4%	17th 78.9%	6th 82.1%	15th 79.4%	19th 76.6%	11th 80.6%	20th 76.3%	8th 81.1%
81.4%	83%	86%	80%	85%	92%	55%	86%	90%	83%	84%	86%	85%	83%	76%	81%	83%	81%	71%	78%	84%	77%
80.2%	75%	79%	84%	84%	69%	79%	79%	81%	68%	81%	85%	79%	84%	83%	88%	85%	88%	78%	84%	68%	83%
67.7%	66%	67%	70%	70%	66%	75%	64%	70%	67%	69%	70%	72%	67%	70%	70%	70%	66%	68%	62%	60%	63%
75.0%	81%	80%	64%	65%	80%	74%	81%	65%	79%	67%	80%	69%	80%	79%	74%	69%	71%	78%	89%	69%	82%
90.3%	92%	84%	88%	88%	90%	97%	83%	85%	89%	90%	88%	92%	98%	94%	86%	89%	95%	87%	94%	96%	92%
86.0%	85%	88%	84%	90%	95%	84%	92%	88%	94%	84%	82%	92%	85%	78%	86%	86%	86%	91%	81%	73%	81%
84.0%	86%	75%	80%	88%	86%	79%	82%	85%	89%	89%	89%	89%	88%	79%	86%	88%	84%	76%	82%	82%	82%
80.8%	88%	73%	80%	80%	87%	56%	83%	80%	83%	87%	87%	87%	87%	90%	80%	83%	88%	72%	78%	76%	72%
75.0%	79%	65%	66%	71%	78%	62%	69%	74%	71%	69%	74%	83%	79%	83%	73%	74%	86%	76%	77%	86%	80%
69.0%	72%	78%	56%	76%	66%	77%	76%	61%	59%	55%	76%	55%	68%	69%	58%	68%	71%	81%	89%	60%	77%
81.9%	90%	89%	89%	91%	81%	90%	77%	89%	78%	76%	88%	71%	87%	71%	82%	89%	73%	60%	86%	73%	89%
68.8%	75%	81%	57%	69%	82%	69%	60%	64%	63%	53%	75%	59%	67%	67%	65%	71%	67%	72%	86%	58%	85%
84.1%	91%	94%	93%	90%	94%	88%	88%	76%	88%	97%	87%	65%	87%	90%	95%	92%	81%	81%	88%	10%	92%
87.1%	91%	87%	85%	81%	87%	91%	88%	87%	90%	88%	89%	86%	93%	85%	86%	92%	82%	78%	85%	90%	88%
86.4%	94%	92%	93%	92%	91%	85%	82%	85%	83%	88%	86%	70%	89%	91%	91%	91%	85%	69%	87%	86%	84%
80.0%	79%	83%	79%	87%	88%	65%	82%	89%	78%	80%	81%	79%	80%	74%	75%	78%	80%	89%	77%	82%	76%
72.4%	78%	85%	76%	81%	74%	81%	73%	61%	68%	68%	64%	73%	65%	63%	85%	82%	62%	72%	73%	64%	73%
61.7%	70%	65%	65%	72%	56%	37%	56%	65%	62%	58%	64%	65%	60%	53%	64%	67%	60%	56%	58%	75%	68%
70.1%	77%	59%	69%	78%	58%	55%	81%	78%	69%	75%	65%	68%	78%	70%	78%	75%	65%	61%	57%	79%	77%
86.0%	84%	82%	85%	84%	93%	94%	86%	97%	99%	86%	89%	92%	90%	82%	73%	79%	85%	81%	84%	81%	80%
87.8%	88%	91%	84%	82%	92%	76%	93%	91%	92%	87%	93%	87%	95%	92%	91%	92%	89%	83%	87%	74%	84%
87.7%	88%	90%	82%	85%	86%	74%	95%	79%	86%	92%	90%	78%	91%	95%	95%	91%	88%	86%	87%	91%	92%
81.8%	90%	80%	84%	85%	85%	74%	87%	85%	79%	84%	83%	68%	76%	76%	90%	88%	69%	83%	84%	83%	84%
88.2%	96%	99%	93%	93%	87%	88%	94%	81%	92%	96%	89%	66%	91%	88%	91%	94%	87%	63%	90%	85%	90%
88.5%	92%	87%	90%	83%	88%	87%	88%	84%	90%	89%	91%	84%	93%	89%	91%	87%	88%	89%	90%	87%	91%
80.5%	87%	79%	82%	87%	83%	75%	76%	73%	80%	84%	84%	71%	82%	83%	89%	82%	79%	74%	80%	83%	78%
72.9%	80%	73%	76%	78%	72%	53%	72%	77%	74%	72%	68%	77%	70%	59%	84%	81%	75%	75%	70%	71%	73%
86.7%	86%	95%	86%	88%	95%	68%	91%	96%	89%	91%	81%	91%	84%	77%	92%	91%	84%	81%	81%	84%	90%
70.8%	71%	74%	75%	76%	75%	65%	79%	82%	58%	55%	73%	49%	72%	62%	73%	70%	67%	76%	75%	78%	81%
75.1%	74%	83%	80%	80%	89%	75%	71%	65%	71%	69%	79%	75%	72%	70%	71%	74%	82%	81%	76%	77%	63%
84.0%	91%	82%	89%	86%	87%	83%	82%	80%	82%	88%	84%	69%	87%	88%	88%	90%	77%	69%	87%	86%	90%
83.5%	85%	84%	81%	89%	85%	76%	87%	81%	84%	81%	81%	79%	84%	81%	83%	82%	85%	83%	89%	87%	87%
61.5%	57%	62%	65%	57%	61%	70%	59%	65%	62%	64%	65%	67%	62%	65%	58%	65%	61%	56%	57%	55%	58%
82.6%	88%	81%	83%	84%	85%	81%	79%	89%	88%	89%	82%	81%	84%	71%	84%	86%	82%	75%	73%	88%	82%
68.2%	79%	76%	68%	68%	59%	57%	60%	63%	62%	66%	69%	66%	79%	81%	61%	65%	74%	75%	79%	59%	67%
79.3%	80%	86%	85%	79%	71%	88%	86%	85%	81%	79%	77%	85%	81%	82%	67%	59%	81%	78%	83%	72%	81%
84.6%	93%	83%	87%	83%	87%	83%	83%	83%	83%	87%	81%	75%	87%	89%	91%	89%	77%	74%	87%	83%	92%
90.5%	86%	99%	93%	90%	89%	97%	93%	84%	93%	90%	93%	84%	89%	89%	87%	94%	97%	88%	87%	89%	89%
85.8%	95%	91%	97%	92%	91%	67%	90%	91%	87%	93%	82%	83%	85%	80%	93%	91%	84%	76%	75%	73%	85%
92.3%	99%	99%	98%	94%	98%	93%	96%	98%	99%	98%	98%	96%	99%	98%	0%	98%	98%	100%	94%	91%	95%
82.3%	87%	85%	86%	86%	94%	79%	86%	91%	86%	89%	86%	77%	81%	80%	85%	83%	73%	64%	73%	78%	79%
78.3%	80%	83%	77%	76%	77%	77%	84%	82%	82%	72%	82%	83%	85%	83%	61%	78%	79%	75%	79%	73%	76%
88.7%	88%	92%	94%	92%	92%	92%	84%	88%	93%	83%	91%	85%	89%	90%	90%	89%	84%	93%	89%	84%	81%

Model Similarity Dendrogram

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