	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	2nd 83.1%	4th 82.3%	6th 81.3%	1st 83.5%	14th 78.8%	21st 74.2%	12th 79.6%	8th 80.9%	10th 80.3%	15th 78.6%	7th 80.9%	9th 80.4%	11th 79.9%	19th 76.9%	5th 81.9%	3rd 82.4%	16th 78.6%	20th 74.3%	18th 77.1%	13th 79.2%	17th 78.1%
80.8%	85%	78%	72%	78%	89%	67%	76%	82%	82%	75%	83%	90%	88%	82%	79%	80%	89%	81%	84%	80%	77%
76.7%	74%	78%	68%	84%	83%	92%	72%	71%	62%	67%	76%	88%	78%	92%	68%	70%	80%		91%	73%	67%
72.9%	72%	72%	85%	78%	65%	76%	70%	79%	70%	76%	70%	70%	65%	70%	74%	76%	64%	70%	67%	92%	70%
81.5%	87%	88%	91%	88%	10%	77%	87%	86%	86%	86%	85%	88%	89%	76%	87%	91%	83%	73%	82%	80%	92%
90.5%	91%	97%	86%	91%	85%	88%	88%	90%	85%	97%	97%	92%	94%	97%	91%	100%	98%	87%	94%	76%	76%
85.8%	90%	89%	81%	89%	96%	87%	87%	96%	86%	84%	86%	83%	87%	76%	77%	86%	83%	94%	79%	78%	87%
84.4%	86%	82%	84%	88%	82%	79%	85%	89%	94%	78%	86%	91%	82%	74%	84%	86%	85%	93%	86%	81%	77%
74.7%	78%	71%	70%	74%	81%	46%	75%	88%	84%	72%	71%	85%	74%	63%	92%	84%	72%		65%		74%
76.6%	80%	70%	60%	70%	81%	54%	69%	68%	69%	73%	77%	73%	79%	73%	77%	80%	95%	97%	70%	97%	97%
88.1%	91%	95%	84%	91%	91%	96%	83%	80%	92%	87%	93%	97%	90%	89%	88%	89%	70%	80%	96%	84%	84%
84.2%	89%	90%	93%	91%	80%	90%	88%	91%	85%	79%	92%	91%	72%	75%	82%	76%	88%	68%	90%	76%	82%
83.7%	90%	82%	90%	88%	77%	89%	83%	93%	81%	81%	81%	87%	84%	84%	88%	86%	81%	71%	89%	76%	76%
87.8%	93%	92%	87%	91%	89%	85%	89%	82%	88%	95%	89%	82%	89%	88%	92%	90%	88%	74%	85%		88%
83.6%	89%	86%	85%	80%	90%	76%	91%	85%	84%	75%	91%	92%	85%	92%	76%	88%	73%	78%	85%	85%	69%
84.8%	76%	87%	90%	87%	80%	78%	88%	90%	85%	82%	90%	89%	87%	87%	83%	84%	87%	79%	81%	90%	80%
72.9%	82%	77%	71%	83%	78%	64%	68%	77%	71%	68%	70%	75%	77%	61%	77%	76%	72%	62%	72%	76%	74%
65.2%	73%	74%	82%	78%	71%	47%	69%	59%	66%	64%	71%	57%	55%	57%	81%	69%	55%	50%	61%	61%	69%
65.0%	71%	64%	63%	67%	67%	42%	57%	72%	66%	63%	60%	66%	66%	43%	74%	71%	68%	76%	62%	70%	77%
61.4%	73%	50%	73%	69%	68%	51%	62%	52%	59%	64%	55%	52%	66%	63%	78%	71%	59%	50%	51%	62%	61%
82.8%	85%	76%	75%	84%	92%	89%	84%	90%	86%	86%	81%	87%	86%	80%	79%	79%	88%	83%	81%	67%	81%
85.2%	86%	88%	86%	85%	85%	73%	90%	86%	92%	83%	87%	89%	88%	79%	86%	93%	89%	69%	74%	89%	92%
83.6%	84%	86%	88%	83%	87%	74%	84%	87%	88%	82%	84%	84%	87%	87%	80%	76%	90%	83%	73%	87%	81%
76.3%	76%	80%	75%	78%	81%	74%	80%	79%	77%	74%	81%	67%	77%	82%	76%	77%	73%	70%	75%	79%	72%
85.4%	85%	90%	87%	88%	94%	84%	81%	81%	90%	88%	85%	81%	86%	89%	87%	94%	84%	64%	83%	85%	87%
79.8%	83%	81%	87%	85%	84%	75%	85%	77%	79%	74%	87%	83%	77%	85%	79%	81%	55%	79%	88%	87%	65%
73.9%	74%	75%	71%	74%	78%	72%	69%	62%	65%	77%	76%	79%	75%	81%	72%	74%	83%	78%	76%	82%	59%
73.5%	82%	74%	72%	83%	72%	49%	70%	78%	73%	76%	63%	77%	74%	60%	83%	77%	75%	74%	71%	84%	77%
76.5%	90%	83%	79%	82%	80%	62%	81%	88%	90%	75%	75%	79%	76%	66%	81%	86%	74%	67%	61%	73%	59%
72.9%	76%	88%	87%	88%	70%	73%	72%	68%	72%	65%	69%	67%	69%	70%	79%	72%	70%	67%	74%	64%	71%
72.6%	77%	80%	74%	82%	79%	62%	61%	75%	67%	67%	65%	72%	72%	67%	75%	73%	73%	83%	77%	71%	72%
86.4%	89%	86%	93%	91%	89%	90%	79%	80%	83%	88%	93%	80%	90%	89%	91%	95%	82%	65%	86%	83%	92%
87.6%	88%	88%	75%	82%	95%	84%	90%	81%	91%	84%	91%	91%	95%	91%	90%	85%	97%	90%	93%	69%	90%
61.1%	61%	61%	73%	66%	54%	64%	59%	67%	58%	64%	58%	58%	54%	58%	58%	66%	53%	58%	56%	79%	58%
83.9%	90%	89%	86%	88%	76%	82%	90%	90%	85%	86%	85%	89%	84%	62%	87%	88%	82%	69%	72%	90%	91%
70.1%	77%	76%	64%	78%	50%	76%	69%	63%	72%	77%	61%	72%	79%	77%	62%	64%	65%	72%	73%	91%	55%
79.4%	90%	89%	91%	88%	73%	65%	88%	91%	83%	87%	83%	74%	81%	68%	73%	77%	82%	70%	66%	66%	83%
84.1%	85%	90%	87%	87%	75%	79%	90%	83%	90%	81%	88%	87%	82%	81%	90%	87%	81%	83%	78%	85%	78%
90.3%	96%	95%	95%	99%	90%	97%	94%	97%	97%	95%	92%	71%	98%	80%	96%	96%	88%	83%	85%	58%	95%
84.5%	93%	87%	94%	92%	85%	68%	89%	93%	84%	81%	88%	86%	86%	68%	90%	91%	84%		72%	82%	77%
92.2%	94%	93%	93%	99%	87%	97%	91%	100%	91%	97%	91%	91%	87%	91%	94%	98%	85%	91%	89%	87%	91%
80.8%	86%	86%	87%	88%	93%	63%	95%	91%	91%		90%	65%	77%	77%	92%	87%	77%	25%	56%	96%	95%
85.2%	89%	93%	84%	84%	89%	74%	78%	79%	82%	78%	93%	94%	82%	92%	89%	91%	83%	83%	84%	80%	89%
76.0%	69%	81%	77%	71%	68%	81%	67%	61%	70%	72%	88%	85%	67%	86%	84%	83%	75%	83%	81%	75%	72%

Model Similarity Dendrogram

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