	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 80.6%	4th 78.8%	19th 70.4%	2nd 80.0%	3rd 79.3%	20th 70.2%	10th 76.7%	7th 77.3%	8th 76.7%	6th 77.3%	12th 75.1%	14th 72.9%	9th 76.7%	11th 75.4%	16th 72.5%	5th 78.4%	15th 72.5%	13th 74.7%	18th 70.8%	21st 68.3%	17th 72.2%
80.4%	88%	81%	78%	86%	88%	60%	76%	82%	83%	83%	83%	84%	80%	87%	78%	81%	70%	85%	75%	83%	78%
80.2%	79%	81%	81%	81%	70%	81%	78%	82%	74%	80%	84%	89%	81%	92%	80%	80%	51%	82%	92%	88%	79%
73.3%	74%	74%	0%	84%	81%	86%	82%	82%	76%	83%	80%	76%	81%	79%	69%	74%	65%	76%	74%	68%	76%
59.2%	58%	66%	58%	48%	63%	62%	70%	57%	57%	59%	61%	46%	71%	74%	50%	43%	56%	58%	66%	58%	63%
91.5%	90%	91%	90%	90%	91%	85%	86%	95%	95%	87%	94%	94%	92%	93%	97%	96%	93%	94%	88%	97%	83%
76.1%	79%	84%	79%	80%	80%	67%	79%	81%	82%	82%	70%	65%	79%	74%	76%	81%	75%	78%	67%	63%	78%
81.4%	90%	82%	76%	93%	87%	87%	76%	89%	84%	80%	81%	93%	75%	70%	88%	81%	79%	77%	79%	75%	68%
65.2%	78%	63%	63%	76%	74%	52%	71%	75%	66%	64%	60%	73%	61%	60%	64%	71%	54%	70%	56%	68%	51%
80.5%	82%	79%	79%	80%	86%	71%	77%	68%	79%	90%	79%	83%	84%	83%	81%	89%	83%	90%	76%	82%	69%
49.8%	51%	56%	41%	56%	58%	51%	49%	47%	54%	45%	54%	34%	58%	55%	47%	43%	47%	57%	57%	36%	49%
84.2%	91%	92%	92%	93%	83%	83%	90%	90%	87%	78%	90%	76%	78%	72%	88%	87%	71%	63%	92%	87%	85%
46.4%	52%	63%	41%	41%	57%	41%	47%	46%	47%	45%	47%	42%	58%	54%	0%	57%	57%	43%	46%	44%	46%
88.0%	87%	94%	92%	95%	90%	81%	87%	91%	89%	93%	84%	84%	85%	85%	93%	93%	84%	84%	81%	84%	92%
89.2%	90%	93%	91%	91%	89%	88%	92%	87%	91%	92%	88%	75%	91%	92%	90%	91%	89%	81%	86%	92%	94%
86.5%	94%	90%	93%	93%	88%	86%	84%	89%	88%	87%	87%	85%	88%	87%	91%	91%	85%	75%	74%	82%	79%
72.2%	84%	73%	76%	85%	76%	52%	71%	77%	73%	69%	76%	76%	73%	70%	75%	78%	64%	69%	63%	70%	67%
64.4%	66%	84%	68%	72%	70%	63%	66%	54%	68%	64%	56%	52%	64%	57%	70%	74%	68%	55%	55%	54%	72%
62.5%	67%	64%	65%	71%	74%	38%	59%	67%	63%	59%	60%	66%	55%	60%	67%	62%	54%	79%	54%	70%	59%
73.1%	78%	70%	80%	79%	70%	53%	89%	76%	72%	78%	71%	68%	70%	66%	78%	73%	79%	76%	69%	75%	65%
74.9%	84%	74%	70%	84%	88%	81%	77%	83%	75%	79%	76%	86%	76%	81%		77%	79%	73%	76%	10%	70%
80.2%	89%	91%	86%	86%	75%	67%	96%	97%	89%	85%	87%	84%	88%	80%	86%	90%	77%	79%	66%	10%	77%
80.7%	98%	81%	78%	89%	86%	63%	87%	76%	85%	81%	81%	84%	81%	77%	83%	83%	77%	84%	69%	75%	76%
74.8%	88%	79%	83%	88%	84%	69%	76%	75%	77%	79%	83%	52%	79%	79%	0%	83%	87%	74%	78%	83%	75%
87.3%	95%	92%	89%	95%	89%	74%	92%	85%	93%	96%	80%	76%	93%	88%	94%	91%	86%	82%	76%	85%	82%
86.3%	86%	89%	92%	92%	89%	90%	88%	86%	87%	88%	88%	78%	89%	87%	83%	89%	87%	82%	77%	82%	84%
79.0%	87%	75%	75%	79%	82%	71%	72%	66%	75%	85%	82%	78%	81%	85%	85%	82%	84%	75%	81%	80%	78%
73.9%	81%	75%	82%	82%	76%	50%	74%	76%	78%	75%	64%	81%	75%	63%	81%	77%	71%	71%	69%	79%	72%
70.0%	80%	77%	76%	79%	71%	54%	75%	79%	76%	72%	55%	74%	71%	61%	79%	72%	60%	73%	59%	70%	57%
54.6%	50%	68%	57%	57%	72%	48%	53%	55%	48%	49%	55%	24%	49%	53%	64%	65%	55%	62%	51%	62%	49%
65.0%	68%	58%	68%	68%	77%	59%	59%	67%	68%	64%	74%	64%	59%	64%	65%	65%	67%	68%	62%	59%	61%
78.5%	98%	88%	99%	76%	88%	87%	81%	90%	84%	92%	83%	85%	84%	87%	0%	89%	83%	83%	75%	10%	86%
68.0%	72%	75%	0%	64%	67%	63%	66%	66%	72%	65%	68%	72%	67%	69%	81%	74%	81%	72%	75%	85%	75%
66.7%	67%	67%	0%	77%	74%	78%	75%	75%	69%	76%	73%	69%	74%	72%	65%	68%	61%	69%	67%	57%	67%
81.3%	88%	75%	85%	86%	90%	78%	79%	88%	83%	89%	80%	86%	81%	71%	82%	83%	78%	71%	73%	82%	79%
56.6%	65%	71%	58%	58%	48%	54%	45%	52%	54%	57%	54%	52%	63%	73%	47%	60%	62%	55%	68%	56%	36%
75.5%	77%	79%	81%	80%	76%	81%	82%	82%	68%	78%	73%	75%	78%	70%	77%	83%	72%	73%	64%	61%	76%
89.0%	95%	97%	93%	85%	85%	94%	90%	87%	91%	95%	88%	86%	91%	88%	96%	92%	85%	87%	73%	85%	87%
89.4%	87%	92%	95%	90%	95%	94%	92%	94%	95%	97%	80%	77%	97%	93%	91%	98%	77%	83%	87%	71%	93%
71.6%	88%	76%	73%	84%	76%	60%	79%	80%	76%	71%	66%	73%	76%	61%	82%	77%	59%	65%	58%	61%	62%
89.2%	95%	91%	0%	99%	98%	97%	100%	100%	93%	100%	98%	93%	98%	96%	88%	91%	85%	93%	91%	80%	88%
81.3%	85%	79%	86%	88%	91%	72%	89%	89%	86%	89%	77%	76%	80%	80%	84%	82%	70%	86%	58%	80%	81%
69.3%	73%	70%	71%	71%	73%	58%	72%	70%	66%	68%	77%	76%	72%	76%	69%	70%	69%	73%	60%	64%	58%
81.7%	92%	88%	89%	90%	85%	89%	68%	72%	83%	78%	82%	74%	72%	77%	81%	87%	82%	87%	81%	74%	84%

Model Similarity Dendrogram

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