	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 80.2%	5th 78.1%	4th 78.4%	6th 77.6%	16th 73.7%	19th 72.2%	7th 77.5%	8th 76.9%	11th 76.3%	10th 76.5%	9th 76.8%	13th 74.2%	12th 76.2%	15th 73.9%	3rd 78.5%	2nd 79.1%	17th 73.7%	18th 72.3%	14th 74.0%	20th 72.0%	21st 70.6%
75.9%	80%	83%	72%	73%	69%	77%	75%	74%	71%	74%	79%	88%	80%	79%	70%	78%	73%	71%	85%	71%	71%
84.2%	88%	89%	89%	79%	83%	89%	92%	84%	76%	84%	86%	85%	92%	85%	83%	88%	80%	79%	89%	77%	72%
63.8%	68%	56%	60%	60%	60%	72%	68%	71%	60%	72%	72%	77%	60%	68%	60%	66%	62%	60%	65%	39%	64%
83.7%	82%	83%	88%	88%	92%	80%	90%	89%	83%	95%	100%	92%	85%	81%	90%	90%	82%	84%	10%	91%	82%
89.1%	91%	95%	93%	93%	89%	85%	96%	90%	91%	95%	93%	89%	95%	97%	93%	90%	92%	84%	89%	66%	65%
92.2%	98%	93%	93%	93%	93%	94%	94%	89%	90%	96%	98%	88%	88%	82%	91%	92%	96%	95%	88%	88%	98%
77.8%	81%	76%	81%	79%	80%	73%	71%	84%	79%	80%	82%	72%	79%	80%	79%	80%	80%	73%	75%	72%
80.4%	93%	84%	75%	80%	77%	52%	75%	89%	83%	77%	85%	85%	86%	79%	84%	91%	89%	82%	76%	73%	73%
80.9%	81%	77%	73%	77%	83%	69%	75%	85%	80%	83%	82%	77%	80%	78%	80%	79%	99%	88%	77%	88%	88%
86.8%	88%	88%	79%	79%	92%	92%	82%	80%	79%	91%	84%	92%	88%	92%	89%	91%	79%	82%	92%	92%	91%
67.0%	68%	76%	74%	82%	68%	85%	76%	79%	68%	63%	67%	72%	58%	52%	68%	57%	49%	47%	82%	73%	43%
82.6%	93%	82%	91%	91%	83%	76%	84%	88%	79%	73%	81%	88%	71%	75%	83%	85%	81%	74%	88%	91%	77%
79.4%	88%	82%	87%	88%	78%	80%	82%	83%	84%	81%	78%	75%	75%	75%	84%	86%	79%	78%	77%	64%	64%
71.2%	78%	83%	78%	71%	81%	60%	73%	70%	78%	77%	70%	56%	73%	63%	74%	71%	64%	66%	84%	66%	60%
67.4%	70%	72%	67%	65%	61%	63%	71%	70%	72%	67%	66%	68%	67%	67%	71%	66%	67%	62%	65%	71%	68%
72.1%	75%	72%	77%	78%	77%	73%	73%	72%	65%	73%	73%	73%	74%	78%	76%	74%	65%	61%	74%	66%	66%
61.0%	72%	73%	67%	64%	69%	58%	69%	49%	62%	59%	68%	54%	53%	62%	64%	67%	54%	35%	61%	63%	59%
71.1%	82%	69%	80%	80%	83%	56%	68%	78%	68%	66%	63%	62%	71%	68%	73%	79%	73%	65%	74%	63%	73%
67.7%	79%	57%	73%	70%	46%	56%	70%	80%	73%	80%	63%	65%	80%	66%	75%	80%	74%	57%	53%	56%
69.3%	77%	60%	77%	69%	63%	69%	67%	71%	70%	71%	69%	68%	70%	70%	70%	74%	68%	68%	68%	68%
79.0%	86%	83%	77%	78%	78%	69%	87%	75%	80%	86%	84%	78%	87%	83%	78%	88%	66%	79%	73%	80%	64%
76.1%	86%	82%	82%	80%	77%	64%	85%	79%	76%	77%	70%	73%	81%	70%	81%	81%	76%	71%	67%	75%	66%
77.2%	80%	84%	84%	79%	74%	66%	74%	71%	84%	68%	85%	79%	57%	60%	83%	85%	89%	88%	72%	85%	75%
79.2%	81%	73%	82%	80%	80%	79%	82%	84%	83%	82%	77%	75%	83%	84%	85%	80%	80%	72%	72%	79%	70%
70.2%	69%	75%	77%	71%	81%	65%	77%	67%	76%	77%	77%	52%	70%	59%	70%	78%	56%	62%	77%	68%	70%
61.6%	62%	71%	61%	69%	71%	61%	60%	51%	50%	67%	66%	66%	70%	69%	64%	67%	50%	52%	63%	59%	44%
75.2%	78%	82%	74%	74%	75%	65%	76%	77%	82%	71%	64%	79%	81%	80%	81%	78%	72%	73%	81%	57%	80%
73.6%	79%	81%	79%	76%	79%	52%	73%	79%	77%	69%	70%	67%	72%	65%	82%	79%	71%	75%	64%	71%	86%
72.6%	75%	77%	79%	74%	73%	73%	74%	65%	73%	69%	73%	73%	69%	57%	73%	77%	73%	73%	73%	73%	78%
77.6%	87%	86%	80%	82%	65%	72%	72%	87%	77%	69%	77%	85%	72%	73%	83%	75%	81%	85%	89%	61%	72%
74.4%	75%	71%	73%	77%	71%	71%	74%	73%	77%	73%	73%	75%	79%	77%	73%	77%	72%	80%	73%	74%
69.6%	62%	79%	75%	75%	75%	62%	66%	63%	75%	62%	62%	58%	75%	66%	75%	68%	72%	75%	69%	75%	73%
76.6%	83%	66%	70%	70%	70%	83%	79%	82%	70%	83%	83%	87%	70%	79%	70%	76%	72%	70%	76%	97%	72%
70.5%	73%	74%	71%	68%	41%	71%	74%	77%	81%	71%	74%	68%	69%	68%	71%	81%	73%	72%	65%	68%
76.9%	84%	80%	81%	85%	40%	78%	71%	81%	72%	69%	73%	78%	81%	76%	88%	83%	76%	80%	88%	73%
79.0%	83%	84%	77%	87%	82%	71%	81%	81%	84%	90%	84%	70%	71%	70%	84%	87%	75%	76%	71%	64%	86%
84.4%	89%	89%	85%	84%	80%	80%	90%	81%	89%	80%	83%	81%	88%	87%	91%	94%	84%	77%	78%	78%
78.6%	90%	78%	91%	84%	95%	88%	100%	93%	86%	89%	83%	61%	80%	75%	82%	81%	63%	55%	71%	53%	53%
62.0%	67%	63%	70%	70%	64%	59%	63%	60%	63%	60%	63%	62%	63%	62%	67%	60%	47%	63%	65%	60%	51%
94.4%	93%	94%	98%	98%	98%	89%	93%	90%	98%	89%	89%	84%	98%	93%	98%	95%	99%	98%	96%	98%
77.6%	84%	80%	84%	88%	53%	74%	81%	79%	68%	82%	84%	77%	79%	79%	78%	80%	75%	77%	76%	74%
85.0%	89%	91%	88%	78%	71%	88%	86%	97%	97%	92%	73%	76%	93%	80%	93%	82%	83%	72%	85%	79%	91%
60.7%	60%	67%	59%	51%	50%	65%	62%	39%	54%	57%	75%	62%	62%	68%	67%	64%	59%	74%	68%	56%	56%

Model Similarity Dendrogram

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