	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 85.7%	4th 84.0%	9th 82.7%	2nd 85.0%	10th 82.7%	20th 77.6%	11th 82.6%	13th 81.5%	12th 81.9%	8th 82.8%	5th 83.8%	17th 79.1%	7th 83.7%	14th 80.9%	6th 83.8%	3rd 84.5%	18th 78.3%	21st 76.7%	16th 79.6%	19th 78.3%	15th 79.9%
85.0%	94%	87%	72%	87%	85%	64%	84%	87%	78%	83%	89%	86%	91%	80%	94%	91%	91%	91%	79%	85%	87%
88.1%	86%	86%	92%	93%	88%	95%	91%	84%	86%	90%	92%	88%	87%	89%	90%	89%	75%	85%	92%	83%	90%
74.3%	75%	67%	79%	79%	75%	75%	70%	74%	71%	78%	79%	72%	72%	72%	73%	66%	78%	76%	62%	97%	70%
90.5%	94%	86%	92%	91%	94%	90%	91%	93%	96%	92%	92%	88%	91%	88%	94%	97%	85%	90%	84%	81%	91%
89.7%	94%	90%	81%	90%	90%	96%	89%	96%	94%	96%	96%	94%	95%	92%	92%	97%	82%	70%	86%	88%	75%
87.4%	89%	95%	89%	94%	95%	93%	91%	94%	96%	87%	88%	75%	90%	77%	77%	80%	86%	88%	83%	77%	92%
79.5%	83%	81%	82%	85%	81%	74%	80%	92%	87%	74%	83%	64%	76%	77%	79%	84%	74%	73%	87%		74%
82.1%	86%	81%	78%	79%	68%	52%	84%	97%	93%	84%	83%	80%	85%	76%	90%	92%	84%	87%	71%	83%	92%
84.5%	85%	82%	75%	82%	87%	70%	78%	91%	81%	94%	93%	88%	94%	92%	87%	87%	91%	82%	84%	76%	76%
86.5%	90%	95%	84%	86%	88%	91%	88%	82%	87%	88%	87%	92%	88%	87%	82%	90%	77%	80%	90%	78%	87%
79.5%	85%	91%	92%	92%	69%	88%	79%	90%	78%	77%	81%	78%	80%	78%	79%	72%	65%	69%	85%	56%	86%
91.1%	91%	93%	93%	96%	96%	94%	92%	94%	90%	92%	87%	93%	95%	90%	94%	92%	85%	77%	95%	80%	94%
86.8%	82%	92%	83%	86%	86%	92%	91%	80%	88%	91%	94%	73%	95%	88%	92%	91%	80%	79%	85%	86%	89%
82.7%	90%	87%	86%	84%	91%	80%	92%	74%	83%	78%	91%	73%	84%	93%	78%	81%	68%	77%	89%	79%	78%
87.2%	94%	90%	94%	94%	80%	85%	89%	85%	87%	87%	90%	81%	89%	91%	89%	85%	85%	86%	84%	85%	81%
83.0%	94%	88%	91%	89%	81%	67%	84%	77%	73%	86%	87%	82%	89%	72%	93%	95%	75%	75%	84%	83%	77%
67.1%	74%	74%	74%	75%	71%	58%	71%	50%	58%	63%	75%	77%	56%	58%	71%	74%	63%	61%	74%	62%	71%
68.7%	75%	67%	70%	80%	67%	50%	58%	63%	62%	60%	60%	70%	70%	58%	81%	82%	79%	75%	70%	70%	76%
57.1%	63%	48%	70%	68%	63%	45%	63%	56%	55%	67%	56%	52%	56%	57%	79%	73%	50%	44%	42%	44%	49%
85.5%	85%	71%	75%	80%	91%	84%	81%	86%	91%	81%	86%	94%	90%	86%	80%	87%	91%	84%	87%	95%	90%
86.5%	94%	93%	87%	87%	91%	76%	97%	81%	94%	90%	90%	84%	95%	90%	87%	84%	76%	76%	77%	88%	80%
86.5%	87%	89%	83%	82%	94%	83%	88%	89%	86%	86%	94%	82%	89%	88%	91%	91%	88%	72%	79%	86%	89%
77.1%	76%	72%	76%	81%	79%	87%	80%	88%	77%	73%	79%	67%	87%	92%	75%	76%	75%	67%	76%	71%	65%
87.9%	92%	90%	95%	90%	89%	91%	85%	86%	85%	95%	91%	74%	92%	87%	85%	97%	88%	78%	79%	87%	89%
80.7%	87%	81%	84%	81%	94%	78%	90%	75%	82%	76%	97%	69%	79%	90%	72%	91%	66%	73%	91%	73%	66%
74.1%	83%	79%	74%	81%	84%	70%	76%	65%	72%	78%	77%	71%	79%	79%	76%	80%	62%	58%	81%	74%	58%
72.1%	87%	74%	71%	78%	71%	55%	64%	72%	71%	76%	64%	73%	75%	64%	76%	80%	65%	80%	68%	68%	82%
84.2%	87%	90%	81%	87%	94%	63%	82%	95%	91%	87%	84%	88%	86%	67%	96%	90%	83%	89%	66%	81%	82%
77.4%	85%	94%	88%	90%	86%	71%	86%	72%	71%	73%	72%	70%	70%	73%	85%	74%	76%	70%	72%	72%	76%
76.0%	77%	87%	75%	90%	83%	67%	65%	83%	82%	71%	74%	70%	74%	74%	82%	78%	67%	85%	78%	67%	67%
83.7%	88%	83%	90%	82%	86%	80%	83%	79%	82%	81%	88%	76%	86%	88%	90%	89%	82%	77%	84%	83%	81%
77.7%	78%	84%	71%	71%	75%	75%	80%	76%	79%	72%	71%	78%	78%	78%	77%	80%	72%	87%	89%	80%	80%
69.2%	70%	64%	75%	76%	72%	72%	67%	71%	68%	75%	75%	69%	69%	69%	67%	65%	75%	61%	59%	67%	67%
83.8%	86%	84%	80%	91%	89%	77%	86%	89%	95%	88%	86%	82%	73%	75%	84%	90%	84%	78%	79%	70%	93%
77.0%	94%	88%	81%	81%	53%	91%	69%	77%	74%	80%	68%	85%	90%	96%	70%	53%	79%	73%	84%	72%	59%
82.6%	86%	87%	86%	84%	71%	81%	91%	86%	90%	87%	85%	84%	88%	79%	68%	85%	82%	76%	75%	83%	81%
85.4%	88%	87%	83%	83%	85%	89%	87%	73%	86%	85%	90%	76%	88%	90%	81%	92%	88%	81%	91%	86%	84%
87.3%	99%	95%	95%	95%	84%	98%	88%	95%	87%	96%	89%	77%	94%	75%	98%	97%	78%	56%	86%	69%	83%
85.5%	96%	87%	94%	94%	86%	76%	90%	91%	86%	91%	84%	83%	86%	81%	93%	91%	81%	69%	71%	85%	80%
95.6%	97%	96%	91%	91%	95%	95%	100%	96%	98%	92%	91%	98%	98%	97%	100%	95%	92%	94%	91%	100%	100%
87.6%	95%	95%	92%	95%	93%	69%	91%	86%	82%	92%	95%	79%	89%	75%	94%	91%	88%	83%	73%	90%	92%
80.8%	78%	86%	77%	74%	74%	72%	83%	82%	82%	87%	79%	83%	83%	88%	84%	82%	84%	76%	83%	80%	79%
77.2%	68%	78%	76%	79%	81%	76%	79%	54%	69%	81%	93%	82%	79%	83%	78%	76%	73%	91%	79%	68%	78%

Model Similarity Dendrogram

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