	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	4th 76.3%	9th 75.2%	6th 76.2%	2nd 77.0%	10th 75.0%	21st 67.2%	14th 74.2%	3rd 77.0%	7th 75.8%	13th 74.2%	5th 76.2%	16th 73.0%	8th 75.7%	15th 73.8%	12th 74.9%	1st 77.9%	10th 75.0%	19th 71.3%	17th 71.8%	20th 68.6%	18th 71.4%
78.5%	85%	80%	74%	74%	78%	58%	74%	83%	80%	74%	83%	84%	80%	83%	80%	85%	79%	84%	77%	74%	80%
63.4%	64%	61%	65%	64%	60%	65%	63%	63%	63%	65%	65%	68%	64%	65%	68%	65%	53%	56%	64%	69%	61%
72.9%	73%	64%	80%	80%	68%	78%	62%	77%	72%	77%	77%	82%	68%	78%	66%	76%	83%	76%	62%	66%	66%
83.8%	94%	78%	83%	90%	83%	68%	82%	90%	78%	94%	90%	66%	91%	79%	83%	89%	85%	86%	78%	88%	85%
84.2%	71%	83%	75%	79%	91%	72%	83%	90%	87%	85%	90%	95%	83%	90%	89%	87%	89%	90%	82%	83%	75%
87.4%	95%	95%	95%	94%	95%	93%	87%	80%	81%	87%	86%	70%	87%	73%	95%	91%	90%	82%	90%	82%	87%
58.0%	60%	46%	59%	59%	56%	56%	58%	78%	64%	59%	54%	32%	59%	52%	61%	61%	64%	62%	62%	58%	57%
74.5%	75%	69%	75%	74%	62%	54%	76%	91%	86%	75%	68%	88%	74%	78%	78%	86%	81%	84%	58%	72%	60%
79.0%	83%	79%	63%	63%	70%	65%	70%	83%	70%	75%	87%	95%	87%	82%	95%	88%	86%	78%	83%	78%	78%
79.9%	83%	85%	78%	83%	79%	69%	88%	83%	74%	83%	88%	90%	88%	76%	75%	79%	74%	67%	75%	78%	83%
74.8%	82%	74%	86%	81%	66%	100%	79%	86%	83%	64%	79%	82%	57%	76%	70%	74%	53%	46%	92%	71%	69%
72.2%	80%	80%	72%	86%	77%	75%	60%	81%	70%	73%	77%	69%	68%	67%	70%	64%	81%	62%	69%	68%	68%
84.5%	82%	92%	82%	82%	87%	77%	85%	81%	92%	82%	81%	71%	86%	92%	78%	90%	94%	89%	83%	86%	82%
79.7%	81%	75%	84%	84%	75%	72%	75%	87%	89%	76%	81%	83%	79%	84%	76%	82%	94%	87%	84%	56%	69%
84.0%	86%	87%	90%	85%	88%	74%	88%	78%	88%	77%	83%	78%	84%	88%	83%	84%	87%	85%	80%	84%	88%
69.3%	75%	70%	72%	78%	71%	61%	67%	72%	65%	71%	71%	70%	71%	66%	67%	72%	67%	72%	66%	66%	66%
74.4%	80%	85%	88%	86%	80%	70%	79%	61%	78%	71%	74%	72%	58%	68%	83%	81%	54%	67%	74%		78%
49.7%	56%	46%	58%	54%	46%	29%	39%	61%	55%	45%	46%	56%	53%	42%	51%	56%	43%	55%	46%	52%	55%
60.0%	58%	49%	66%	58%	62%	53%	65%	55%	60%	78%	64%	49%	78%	52%	66%	75%	63%	49%	51%	48%	62%
59.5%	56%	52%	59%	58%	56%	64%	56%	72%	66%	64%	59%	43%	65%	57%	62%	57%	54%	67%	59%	67%	56%
72.3%	79%	81%	68%	71%	79%	60%	80%	75%	80%	70%	77%	79%	79%	72%	80%	82%	89%	71%	56%	10%	80%
82.2%	83%	78%	83%	83%	90%	71%	88%	88%	88%	80%	81%	76%	84%	81%	88%	91%	83%	82%	73%	71%	84%
68.8%	65%	68%	71%	75%	68%	68%	65%	71%	65%	71%	76%	60%	73%	77%	72%	65%	64%	66%	72%	67%	66%
82.8%	83%	83%	83%	80%	89%	86%	78%	77%	89%	80%	91%	68%	87%	86%	77%	88%	91%	83%	79%	80%	80%
71.0%	72%	72%	73%	72%	72%	63%	70%	82%	77%	68%	70%	79%	69%	76%	68%	72%	75%	69%	78%	55%	59%
69.1%	77%	71%	70%	74%	67%	64%	63%	59%	68%	73%	67%	63%	71%	71%	72%	74%	74%	66%	68%	70%	70%
58.5%	70%	59%	55%	61%	60%	44%	47%	58%	64%	60%	55%	64%	63%	54%	59%	69%	60%	57%	59%	55%	55%
82.2%	93%	86%	88%	91%	88%	54%	89%	90%	84%	78%	83%	89%	85%	73%	86%	88%	87%	83%	74%	67%	71%
70.1%	81%	92%	77%	78%	84%	59%	81%	65%	63%	65%	75%	60%	64%	63%	66%	65%	66%	66%	67%	70%	66%
66.5%	64%	67%	63%	79%	100%	50%	60%	71%	66%	63%	64%	59%	71%	64%	67%	63%	65%	70%	73%	58%	59%
78.2%	83%	84%	77%	79%	78%	66%	83%	76%	83%	77%	81%	77%	85%	80%	79%	85%	74%	57%	81%	78%	79%
82.8%	81%	91%	74%	75%	87%	76%	91%	77%	83%	77%	77%	73%	87%	76%	89%	79%	83%	91%	93%	89%	89%
81.5%	83%	73%	90%	89%	77%	87%	73%	87%	81%	87%	87%	91%	77%	88%	79%	85%	81%	75%	71%	75%	75%
66.3%	69%	63%	66%	77%	86%	57%	68%	77%	67%	74%	63%	71%	63%	47%	73%	77%	69%	58%	52%	58%	58%
67.6%	72%	77%	77%	66%	58%	51%	78%	76%	78%	68%	70%	59%	77%	70%	60%	69%	72%	64%	48%	70%	60%
68.3%	65%	70%	72%	77%	56%	63%	72%	77%	64%	77%	75%	64%	68%	71%	60%	72%	71%	52%	66%	71%	72%
84.2%	90%	92%	96%	89%	81%	70%	92%	77%	91%	85%	89%	83%	84%	89%	92%	91%	73%	61%	78%	84%	82%
88.4%	86%	90%	91%	88%	93%	94%	86%	95%	94%	88%	94%	77%	94%	85%	94%	100%	85%	88%	90%	63%	81%
81.3%	81%	84%	90%	87%	84%	67%	86%	80%	84%	82%	86%	85%	86%	82%	82%	91%	74%	66%	70%	77%	83%
58.3%	60%	51%	67%	66%	55%	65%	51%	64%	59%	64%	64%	68%	55%	65%	55%	62%	70%	51%	49%	30%	53%
75.6%	77%	80%	82%	82%	69%	56%	83%	80%	72%	78%	78%	63%	78%	76%	72%	70%	81%	83%	76%	76%	76%
80.9%	79%	84%	77%	77%	83%	80%	86%	84%	82%	77%	85%	93%	92%	88%	75%	82%	74%	72%	84%	75%	70%
83.0%	67%	87%	83%	83%	69%	86%	83%	71%	75%	75%	86%	93%	83%	93%	78%	89%	88%	93%	97%	87%	78%

Model Similarity Dendrogram

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