	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 83.8%	7th 81.7%	2nd 83.2%	16th 75.7%	4th 82.2%	21st 69.3%	9th 80.2%	8th 81.4%	11th 79.8%	4th 82.2%	12th 78.7%	14th 75.9%	10th 80.0%	20th 74.3%	3rd 82.3%	6th 82.0%	15th 75.8%	19th 75.0%	17th 75.7%	13th 76.4%	18th 75.3%
80.7%	89%	87%	90%	85%	88%	68%	78%	84%	72%	83%	79%	83%	83%	79%	85%	81%	72%	88%	75%	74%	72%
80.4%	80%	70%	82%	84%	68%	89%	77%	88%	69%	80%	87%	81%	91%	90%	87%	87%	75%	58%	88%	79%	79%
61.7%	78%	63%	57%	0%	57%	69%	66%	68%	61%	77%	71%	69%	76%	66%	64%	63%	60%	64%	63%	39%	64%
90.9%	90%	88%	91%	97%	95%	92%	93%	89%	90%	96%	85%	97%	89%	83%	91%	83%	89%	90%	94%		96%
90.9%	93%	95%	94%	90%	94%	80%	94%	95%	99%	95%	94%	92%	93%	91%	88%	90%	99%	88%	87%	94%	64%
82.8%	88%	90%	92%	86%	96%	70%	82%	87%	90%	86%	87%	67%	79%	69%	82%	84%	75%	86%	82%	74%	87%
79.5%	82%	80%	82%	82%	76%	73%	77%	82%	82%	84%	74%	76%	80%	79%	84%	81%	87%	84%	76%	78%	70%
73.7%	91%	73%	77%	86%	74%	37%	69%	83%	79%	78%	66%	75%	71%	65%	94%	80%	73%	83%	60%	67%	67%
81.5%	67%	89%	79%	79%	87%	62%	80%	78%	88%	91%	87%	88%	92%	79%	79%	87%	93%	83%	76%	74%	74%
93.5%	96%	97%	96%	96%	97%	97%	92%	89%	95%	98%	97%	97%	96%	97%	96%	95%	68%	79%	97%	94%	94%
83.6%	90%	91%	90%	90%	83%	85%	87%	85%	86%	84%	89%	87%	87%	78%	87%	78%	85%	70%	72%	90%	61%
86.5%	91%	86%	93%	95%	96%	85%	91%	94%	92%	84%	73%	95%	60%	74%	93%	92%	72%	75%	92%	86%	98%
83.7%	75%	87%	86%	79%	86%	85%	83%	86%	85%	84%	87%	88%	84%	86%	81%	87%	81%	82%	83%	81%	81%
89.2%	96%	92%	88%	88%	92%	78%	90%	94%	95%	87%	91%	71%	98%	78%	89%	94%	86%	93%	96%	90%	88%
85.0%	92%	85%	93%	94%	82%	63%	93%	94%	91%	85%	81%	90%	82%	75%	97%	92%	77%	64%	72%	88%	94%
79.2%	87%	84%	87%	87%	89%	59%	78%	82%	81%	80%	71%	73%	82%	68%	83%	88%	79%	78%	85%	78%	64%
58.8%	69%	69%	72%	69%	54%	54%	65%	43%	63%	66%	57%	53%	50%	53%	60%	65%	60%	34%	60%	46%	72%
69.9%	89%	67%	85%	86%	80%	48%	62%	76%	63%	76%	59%	65%	72%	50%	75%	77%	72%	66%	65%	74%	60%
66.0%	67%	56%	68%	55%	86%	45%	57%	72%	73%	87%	62%	43%	71%	73%	87%	84%	81%	47%	51%	62%	58%
77.3%	76%	79%	80%	81%	88%	74%	84%	77%	72%	85%	75%	69%	81%	72%	83%	82%	74%	72%	73%	71%	75%
83.7%	86%	88%	94%	88%	90%	56%	84%	92%	88%	89%	83%	91%	85%	84%	86%	87%	85%	86%	64%	83%	68%
79.0%	78%	77%	83%	85%	85%	67%	85%	82%	80%	79%	76%	79%	80%	76%	75%	80%	79%	85%	67%	82%	78%
75.7%	75%	71%	81%	78%	87%	82%	82%	83%	67%	82%	84%	63%	78%	69%	73%	70%	69%	74%	83%	73%	65%
87.6%	83%	88%	82%	82%	88%	77%	88%	92%	93%	86%	87%	90%	89%	92%	88%	93%	88%	88%	86%	88%	92%
85.8%	88%	89%	86%	85%	90%	85%	91%	90%	93%	88%	91%	69%	89%	71%	77%	84%	85%	90%	93%	85%	83%
74.0%	75%	76%	78%	70%	83%	65%	72%	70%	75%	75%	78%	77%	79%	78%	65%	74%	72%	74%	77%	75%	67%
65.5%	81%	67%	77%	77%	71%	46%	62%	69%	65%	70%	53%	63%	65%	51%	76%	68%	66%	58%	65%	63%	62%
75.0%	89%	88%	80%	80%	91%	49%	78%	87%	79%	81%	71%	62%	77%	55%	87%	88%	77%	57%	54%	66%	79%
74.0%	84%	94%	83%	84%	81%	64%	83%	68%	69%	65%	78%	63%	65%	64%	82%	81%	67%	63%	67%	77%	72%
76.4%	89%	76%	84%	90%	86%	67%	68%	80%	72%	80%	74%	60%	74%	70%	89%	79%	73%	87%	84%	61%	61%
81.6%	90%	82%	91%	93%	94%	61%	91%	86%	89%	86%	78%	75%	83%	75%	73%	78%	82%	64%	71%	83%	89%
79.3%	71%	86%	93%	0%	93%	80%	89%	81%	89%	72%	77%	80%	72%	83%	80%	86%	89%	89%	86%	85%	85%
58.6%	64%	59%	52%	0%	52%	64%	56%	63%	56%	72%	67%	64%	71%	62%	52%	59%	56%	56%	58%	89%	59%
76.5%	85%	76%	78%	79%	72%	70%	77%	81%	78%	80%	74%	71%	76%	69%	80%	81%	80%	81%	70%	73%	76%
83.3%	95%	97%	98%	96%	86%	69%	75%	73%	72%	79%	82%	86%	82%	76%	97%	89%	68%	85%	87%	84%	73%
85.1%	96%	91%	94%	95%	72%	68%	92%	93%	91%	91%	88%	78%	90%	78%	80%	85%	81%	77%	79%	84%	85%
79.7%	84%	82%	84%	85%	85%	67%	84%	82%	83%	78%	81%	88%	74%	74%	92%	87%	74%	74%	73%	69%	73%
87.4%	93%	90%	93%	82%	77%	93%	95%	93%	85%	97%	91%	79%	96%	85%	89%	91%	60%	88%	90%	84%	85%
76.0%	93%	83%	82%	84%	82%	58%	82%	94%	79%	86%	77%	60%	84%	60%	92%	87%	63%	50%	61%	80%	58%
86.3%	94%	91%	84%	0%	84%	97%	88%	96%	88%	95%	100%	96%	96%	94%	92%	91%	88%	92%	91%	65%	91%
75.2%	74%	75%	71%	68%	89%	60%	81%	83%	87%	76%	72%	67%	70%	72%	85%	76%	70%	74%	60%	89%	80%
75.8%	79%	80%	77%	77%	76%	67%	82%	73%	73%	80%	72%	76%	81%	84%	75%	73%	74%	72%	73%	69%	79%
65.9%	73%	81%	70%	70%	54%	57%	67%	45%	54%	63%	79%	68%	67%	69%	71%	71%	56%	77%	67%	62%	62%

Model Similarity Dendrogram

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