	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 82.1%	4th 80.8%	8th 80.3%	2nd 81.4%	11th 79.7%	20th 73.5%	7th 80.3%	6th 80.5%	13th 78.8%	10th 79.9%	9th 80.2%	21st 73.4%	5th 80.5%	17th 76.9%	12th 79.3%	3rd 81.2%	14th 78.3%	19th 74.9%	18th 75.6%	16th 77.1%	15th 77.1%
79.3%	84%	84%	78%	84%	79%	55%	81%	82%	78%	78%	83%	84%	81%	74%	87%	82%	79%	76%	71%	82%	84%
86.7%	86%	86%	88%	92%	84%	93%	84%	95%	82%	93%	92%	79%	91%	90%	91%	86%	88%	72%	86%	77%	85%
66.4%	64%	64%	64%	64%	64%	72%	66%	68%	64%	72%	72%	66%	66%	72%	66%	72%	64%	66%	64%	62%	62%
65.0%	65%	66%	59%	54%	67%	73%	75%	62%	57%	65%	74%	58%	73%	76%	46%	66%	71%	50%	81%	57%	71%
91.7%	93%	92%	91%	88%	89%	95%	91%	88%	92%	92%	94%	93%	94%	94%	91%	95%	89%	97%	88%	95%	85%
84.6%	86%	89%	90%	87%	91%	69%	90%	89%	91%	83%	78%	92%	81%	74%	82%	87%	82%	92%	78%	88%	78%
82.5%	77%	73%	87%	87%	85%	71%	77%	87%	83%	81%	84%	87%	82%	76%	88%	87%	88%	84%	73%	89%	87%
71.8%	80%	63%	72%	74%	76%	53%	73%	69%	73%	78%	77%	76%	72%	69%	72%	71%	77%	73%	62%	71%	76%
84.9%	86%	88%	77%	82%	87%	83%	83%	95%	80%	90%	84%	92%	89%	92%	84%	82%	90%	69%	88%	83%	78%
61.8%	57%	68%	58%	58%	61%	68%	68%	58%	51%	59%	67%	37%	66%	70%	51%	66%	72%	62%	86%	57%	58%
84.3%	89%	91%	92%	86%	80%	92%	84%	88%	86%	87%	90%	74%	88%	72%	90%	90%	73%	59%	89%	81%	89%
56.2%	69%	67%	47%	58%	59%	59%	66%	54%	49%	44%	63%	33%	59%	61%	53%	38%	70%	64%	65%	51%	52%
87.8%	93%	89%	96%	92%	87%	84%	91%	83%	91%	94%	84%	61%	93%	87%	91%	97%	85%	85%	85%	86%	89%
91.3%	94%	96%	93%	89%	89%	96%	89%	93%	90%	92%	93%	89%	95%	90%	96%	92%	84%	86%	88%	91%	93%
84.0%	88%	89%	93%	93%	82%	81%	93%	87%	87%	85%	87%	69%	87%	86%	85%	87%	83%	65%	74%	83%	79%
79.1%	83%	80%	79%	91%	78%	64%	81%	88%	76%	78%	78%	75%	78%	74%	83%	81%	76%	89%	68%	80%	81%
66.9%	69%	71%	71%	75%	68%	71%	68%	57%	70%	66%	68%	68%	66%	57%	79%	78%	57%	48%	68%	61%	69%
62.6%	65%	68%	68%	72%	55%	39%	58%	68%	60%	62%	67%	64%	63%	59%	67%	66%	59%	60%	61%	64%	69%
75.0%	86%	74%	81%	81%	72%	58%	87%	80%	71%	84%	73%	68%	81%	68%	81%	75%	65%	72%	70%	82%	66%
84.8%	84%	77%	81%	91%	92%	86%	83%	95%	89%	86%	87%	91%	86%	77%	78%	89%	89%	71%	78%	89%	81%
85.0%	92%	88%	87%	89%	86%	71%	94%	94%	90%	89%	85%	77%	91%	77%	95%	95%	75%	69%	75%	76%	89%
88.1%	93%	86%	90%	91%	96%	73%	93%	88%	90%	94%	92%	80%	93%	89%	88%	98%	91%	88%	75%	76%	86%
81.3%	95%	84%	87%	86%	86%	71%	78%	70%	83%	85%	81%	60%	71%	78%	89%	84%	76%	87%	83%	89%	84%
89.6%	97%	95%	92%	93%	90%	93%	97%	94%	94%	94%	93%	68%	93%	89%	86%	92%	86%	86%	84%	82%	84%
90.3%	98%	93%	92%	85%	91%	97%	92%	90%	91%	90%	93%	88%	94%	84%	97%	81%	92%	81%	87%	85%	96%
81.6%	89%	80%	83%	84%	86%	72%	78%	79%	81%	86%	83%	74%	83%	79%	85%	87%	81%	82%	78%	79%	84%
70.6%	82%	76%	76%	76%	75%	50%	69%	72%	70%	68%	60%	71%	73%	55%	76%	75%	79%	80%	63%	71%	65%
74.2%	72%	76%	76%	76%	77%	57%	76%	84%	87%	73%	71%	75%	76%	59%	78%	84%	71%	78%	58%	82%	72%
62.1%	63%	68%	69%	69%	58%	66%	71%	54%	51%	51%	67%	37%	67%	67%	65%	60%	60%	70%	69%	62%	61%
66.6%	58%	73%	64%	64%	72%	62%	56%	64%	62%	62%	71%	66%	62%	73%	60%	68%	77%	82%	69%	70%	64%
85.5%	94%	87%	94%	94%	90%	82%	86%	89%	86%	93%	84%	67%	87%	84%	90%	89%	82%	77%	80%	82%	79%
90.7%	94%	94%	94%	94%	94%	85%	91%	90%	93%	86%	85%	91%	92%	85%	89%	86%	89%	91%	94%	91%	96%
61.4%	59%	59%	59%	59%	59%	67%	61%	62%	59%	66%	67%	61%	61%	67%	57%	64%	64%	63%	59%	59%	57%
81.0%	90%	76%	78%	91%	91%	66%	72%	83%	90%	86%	77%	81%	80%	72%	80%	91%	82%	82%	62%	80%	90%
65.1%	73%	81%	65%	65%	55%	66%	57%	61%	61%	59%	66%	59%	72%	84%	48%	65%	67%	68%	83%	67%	45%
81.5%	84%	90%	86%	86%	71%	73%	92%	94%	78%	87%	85%	82%	90%	75%	82%	85%	81%	68%	72%	70%	81%
87.9%	91%	93%	90%	92%	92%	81%	90%	89%	91%	95%	86%	74%	92%	87%	92%	94%	86%	76%	82%	89%	83%
91.0%	85%	97%	96%	93%	94%	86%	97%	88%	96%	92%	94%	81%	99%	85%	97%	92%	81%	97%	85%	81%	94%
79.7%	86%	82%	88%	88%	84%	59%	82%	87%	81%	85%	81%	76%	79%	65%	83%	89%	81%	82%	63%	77%	75%
87.5%	85%	85%	85%	85%	85%	93%	87%	88%	85%	93%	93%	87%	87%	93%	88%	90%	90%	87%	85%	84%	83%
80.0%	86%	80%	92%	92%	90%	67%	90%	86%	89%	82%	76%	86%	74%	78%	85%	83%	78%	23%	72%	88%	82%
76.3%	78%	82%	70%	73%	80%	73%	81%	82%	74%	75%	78%	82%	78%	82%	64%	79%	79%	81%	74%	74%	64%
78.4%	87%	76%	75%	79%	79%	87%	76%	86%	88%	74%	84%	77%	75%	80%	74%	73%	77%	82%	75%	71%	71%

Model Similarity Dendrogram

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