	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	9th 81.6%	4th 82.9%	3rd 83.6%	2nd 84.0%	1st 85.2%	19th 76.5%	10th 81.5%	13th 79.6%	11th 81.0%	12th 80.5%	6th 82.4%	21st 76.2%	7th 82.3%	14th 79.2%	8th 82.0%	5th 82.7%	20th 76.3%	16th 78.4%	15th 78.7%	17th 77.9%	18th 77.6%
81.5%		87%	80%	89%	86%	71%	81%	78%	76%	79%	88%	72%	85%	82%	85%	88%	83%	87%	85%	70%	78%
87.4%		90%	91%	86%	92%	97%	85%	88%	90%	93%	89%	86%	91%	93%	85%	92%	74%	92%	92%	73%	69%
72.8%		65%	77%	77%	73%	73%	68%	71%	68%	77%	74%	70%	73%	68%	73%	76%	74%	70%	65%	96%	69%
91.3%		84%	94%	89%	94%	91%	94%	94%	89%	92%	94%	90%	93%	96%	95%	92%	88%	89%	90%	91%	88%
88.3%		98%	83%	88%	87%	93%	90%	93%	92%	87%	91%	95%	87%	95%	97%	92%	79%	81%	85%	79%	74%
81.2%		88%	83%	87%	87%	80%	84%	92%	83%	80%	80%	85%	84%	73%	68%	84%	78%	84%	80%	70%	74%
80.1%		82%	81%	87%	84%	74%	85%	87%	77%	75%	89%	61%	79%	75%	72%	85%	78%	82%	85%	92%	72%
78.8%		75%	73%	85%	70%	61%	74%	91%	85%	83%	74%	75%	81%	71%	85%	89%	83%	72%	75%	87%	88%
87.0%		88%	90%	88%	92%	73%	78%	80%	83%	94%	95%	93%	95%	91%	84%	90%	93%	82%	79%	76%	96%
84.1%	93%	94%	86%	86%	91%	89%	83%	77%	80%	88%	80%	90%	85%	80%	87%	85%	67%	77%	85%	80%	84%
83.4%		93%	95%	95%	81%	92%	94%	85%	86%	80%	89%	79%	76%	69%	77%	82%	80%	63%	84%	82%	85%
90.7%	87%	94%	98%	99%	95%	92%	90%	93%	87%	90%	86%	92%	95%	89%	97%	79%	76%	82%	98%	95%	91%
85.4%		88%	80%	87%	88%	87%	87%	80%	84%	86%	91%	76%	88%	91%	91%	86%	83%	88%	81%	82%	83%
79.3%		83%	85%	79%	86%	76%	88%	70%	77%	73%	87%	74%	81%	88%	76%	84%	68%	83%	91%	71%	65%
86.2%		91%	92%	89%	94%	84%	90%	84%	90%	84%	91%	80%	90%	87%	86%	81%	85%	79%	83%	82%	82%
83.5%		90%	93%	89%	89%	75%	84%	76%	83%	87%	81%	83%	90%	74%	92%	93%	85%	70%	85%	76%	76%
60.5%		70%	71%	70%	54%	54%	67%	46%	56%	62%	58%	56%	49%	54%	73%	69%	46%	54%	70%	65%	65%
72.0%		68%	84%	84%	90%	50%	64%	68%	70%	73%	63%	67%	76%	61%	75%	83%	73%	78%	73%	70%	70%
62.2%	63%	47%	77%	67%	80%	54%	68%	59%	65%	67%	59%	43%	63%	60%	83%	78%	56%	47%	51%	54%	66%
86.4%	85%	71%	86%	90%	91%	96%	92%	81%	88%	87%	95%	77%	88%	90%	79%	77%	80%	90%	86%	96%	89%
87.1%		92%	85%	86%	94%	80%	98%	77%	95%	89%	93%	87%	96%	91%	88%	79%	87%	86%	79%	68%	93%
85.4%		89%	83%	84%	95%	74%	89%	90%	91%	84%	86%	82%	87%	88%	85%	93%	88%	81%	72%	89%	78%
73.1%	70%	65%	84%	71%	81%	84%	86%	85%	68%	64%	87%	56%	81%	86%	70%	73%	69%	64%	65%	68%	58%
84.0%		87%	83%	89%	89%	87%	84%	83%	87%	86%	94%	74%	87%	91%	87%	93%	87%	77%	84%	53%	79%
78.5%		85%	83%	78%	86%	75%	82%	68%	76%	71%	88%	71%	81%	90%	78%	81%	71%	79%	88%	78%	62%
74.3%		77%	77%	78%	78%	72%	71%	67%	74%	75%	79%	71%	71%	79%	80%	79%	59%	72%	76%	78%	73%
71.8%		72%	77%	79%	77%	51%	67%	67%	72%	75%	60%	78%	80%	65%	79%	72%	79%	76%	71%	63%	75%
78.0%		83%	75%	79%	89%	56%	68%	90%	87%	79%	81%	89%	79%	64%	85%	86%	72%	80%	63%	81%	74%
69.1%	82%	91%	77%	78%	87%	63%	85%	62%	64%	60%	67%	56%	65%	57%	66%	76%	62%	60%	65%	61%	67%
76.2%		85%	80%	85%	93%	68%	63%	78%	79%	72%	76%	60%	84%	79%	67%	78%	65%	82%	84%	79%	66%
85.0%		86%	89%	87%	89%	85%	83%	80%	82%	84%	90%	75%	84%	84%	91%	88%	83%	89%	76%	89%	85%
75.4%		82%	69%	69%	73%	73%	78%	76%	78%	69%	73%	76%	73%	78%	78%	77%	73%	76%	81%	78%	78%
64.8%		59%	71%	71%	67%	67%	62%	65%	62%	71%	67%	64%	67%	62%	64%	63%	65%	64%	59%	63%	63%
85.3%	91%	86%	86%	92%	85%	73%	90%	84%	93%	87%	93%	56%	83%	73%	91%	92%	95%	87%	73%		96%
78.5%		82%	82%	80%	88%	91%	63%	76%	69%	79%	68%	73%	87%	88%	73%	74%	73%	87%	80%	94%	64%
84.5%		90%	96%	96%	74%	74%	90%	94%	86%	94%	84%	83%	90%	72%	81%	78%	84%	81%	71%	85%	88%
87.3%		91%	87%	86%	92%	78%	92%	77%	90%	86%	92%	86%	90%	92%	89%	91%	88%	85%	88%	86%	80%
86.0%		88%	94%	93%	87%	97%	90%	96%	98%	98%	93%	73%	95%	69%	89%	90%	71%	80%	80%	48%	90%
78.3%		83%	87%	84%	84%	65%	82%	93%	81%	74%	76%	82%	80%	70%	84%	86%	68%	71%	64%	84%	68%
96.4%		95%	92%	92%	96%	96%	99%	99%	99%	92%	96%	99%	96%	99%	97%	93%	96%	99%	96%	99%	99%
82.2%		91%	83%	83%	97%	63%	77%	85%	97%	80%	85%	78%	77%	81%	86%	74%	62%	85%	86%	91%	83%
80.1%		82%	78%	82%	80%	73%	81%	82%	77%	87%	75%	81%	80%	80%	84%	84%	80%	80%	81%	75%	79%
75.9%		77%	78%	77%	78%	81%	78%	56%	69%	68%	86%	81%	77%	81%	76%	73%	77%		80%	74%	76%

Model Similarity Dendrogram

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