	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 72.9%	2nd 73.4%	3rd 72.9%	8th 71.8%	18th 68.7%	17th 68.8%	13th 70.0%	14th 69.8%	15th 69.7%	9th 71.7%	1st 73.9%	11th 70.8%	7th 72.6%	5th 72.8%	10th 71.1%	11th 70.8%	19th 68.6%	16th 69.0%	6th 72.8%	20th 68.6%	21st 67.6%
77.4%	88%	76%	76%	82%	76%	62%	81%	77%	75%	69%	76%	75%	82%	77%	82%	84%	74%		82%	82%	72%
43.3%	40%	43%	42%	42%	39%	52%	36%	44%	39%	42%	53%	50%	39%	57%	39%	40%	34%		53%	42%	39%
76.5%	76%	71%	87%	82%	66%	76%	76%	82%	71%	76%	82%	76%	76%	76%	71%	73%	76%	70%	71%	99%	73%
76.0%	86%	82%	77%	82%	74%	56%	79%	86%	79%	82%	71%	75%	79%	71%	77%	77%	75%	62%	72%	78%	77%
71.0%	64%	81%	64%	72%	73%	61%	64%	72%	67%	73%	76%	66%	73%	83%	84%	70%	84%	93%	64%	54%	54%
72.9%	68%	64%	61%	68%	68%	72%	72%	70%	77%	72%	73%	72%	73%	88%	72%	68%	81%	80%	89%	76%	67%
81.8%	83%	84%	80%	85%	79%	82%	87%	76%	87%	78%	93%	90%	93%	90%	71%	74%	73%	86%	90%	71%	66%
71.2%	74%	73%	80%	80%	76%	57%	68%	72%	72%	68%	74%	77%	76%	69%	79%	70%	68%	71%	62%	72%	57%
82.1%	88%	83%	72%	82%	78%	62%	83%	83%	78%	93%	88%	78%	93%	83%	89%	88%	86%	82%	72%	82%	82%
71.5%	76%	69%	67%	67%	82%	67%	67%	67%	67%	78%	75%	75%	75%	75%	72%	67%	67%	66%	70%	76%	76%
50.4%	54%	56%	57%	57%	38%	63%	57%	60%	52%	49%	46%	46%	47%	46%	47%	46%	34%	36%	53%	57%	57%
71.1%	76%	71%	69%	75%	76%	65%	63%	69%	63%	74%	81%	65%	70%	63%	81%	76%	87%	65%	65%	65%	74%
59.8%	53%	65%	59%	59%	59%	73%	55%	48%	64%	57%	70%	56%	61%	59%	56%	59%	60%	65%	70%	50%	57%
78.5%	81%	76%	83%	87%	85%	62%	86%	82%	81%	81%	82%	77%	82%	86%	82%	89%	71%	68%	83%	59%	66%
83.0%	87%	82%	87%	87%	87%	74%	86%	84%	82%	82%	84%	82%	87%	85%	82%	87%	77%		81%	83%	73%
73.7%	79%	75%	86%	67%	67%	62%	76%	82%	80%	63%	71%	75%	82%	74%	76%	79%	76%		80%	63%	60%
58.5%	68%	67%	73%	68%	58%	51%	63%	57%	51%	48%	66%	51%	51%	57%	74%	64%	39%	48%	60%	46%	68%
66.0%	75%	67%	67%	71%	71%	57%	67%	67%	67%	56%	61%	61%	62%	55%	72%	69%	69%		67%	69%	70%
44.6%	46%	33%	47%	48%	64%	26%	46%	45%	40%	51%	45%	33%	46%	34%	64%	56%	42%	41%	31%	52%	46%
75.2%	79%	81%	77%	73%	63%	65%	73%	66%	74%	81%	80%	78%	80%	79%	75%	77%	72%	81%	78%	79%	68%
78.5%	74%	78%	76%	76%	82%	79%	86%	70%	85%	77%	92%	85%	84%	87%	74%	74%	70%	63%	92%	71%	74%
68.1%	62%	70%	70%	68%	68%	87%	62%	58%	67%	72%	71%	54%	68%	73%	62%	68%	67%	73%	77%	73%	61%
80.2%	76%	90%	82%	82%	82%	78%	73%	89%	88%	77%	77%	88%	77%	81%	77%	77%	84%	78%	75%	78%	75%
78.4%	79%	82%	87%	79%	75%	79%	76%	76%	77%	100%	76%	76%	79%	78%	88%	78%	74%	56%	66%	83%	82%
64.4%	68%	72%	67%	67%	77%	54%	68%	75%	68%	60%	72%	68%	65%	66%	60%	68%	49%	71%	68%	51%	39%
74.7%	68%	88%	74%	67%	65%	80%	74%	74%	77%	77%	87%	83%	74%	84%	69%	69%	82%		83%	60%	60%
71.7%	81%	75%	76%	81%	82%	54%	76%	74%	56%	71%	61%	75%	76%	67%	72%	87%	75%	72%	75%	57%	63%
67.0%	66%	74%	68%	72%	50%	72%	70%	61%	56%	80%	74%	67%	71%	66%	66%	69%	70%	63%	64%	61%	68%
77.0%	83%	72%	81%	81%	75%	74%	75%	76%	76%	79%	75%	76%	85%	79%	75%	74%	77%	75%	75%	78%	75%
70.7%	78%	66%	82%	77%	69%	75%	72%	70%	66%	75%	66%	70%	67%	67%	80%	66%	69%	49%	66%	76%	78%
69.0%	69%	74%	71%	56%	71%	79%	62%	57%	61%	73%	74%	78%	71%	73%	55%	55%	69%	76%	72%	77%	75%
92.2%	92%	96%	81%	86%	97%	92%	92%	86%	97%	92%	86%	92%	92%	92%	95%	92%	92%	97%	97%	95%	95%
76.0%	76%	72%	87%	82%	66%	76%	76%	82%	71%	76%	82%	76%	76%	76%	76%	76%	72%	83%	71%	71%	73%
76.0%	82%	81%	80%	65%	69%	80%	79%	74%	82%	82%	86%	76%	77%	76%	76%	83%	58%	77%	76%	67%	71%
67.7%	78%	78%	78%	78%	31%	75%	67%	71%	72%	72%	56%	79%	72%	76%	54%	54%	72%	67%	81%	53%	58%
64.5%	64%	70%	68%	68%	52%	70%	62%	69%	64%	65%	69%	63%	69%	60%	57%	59%	63%	55%	70%	76%	61%
38.1%	39%	42%	42%	30%	38%	50%	33%	20%	33%	42%	50%	28%	33%	42%	33%	29%	33%	59%	47%	33%	44%
90.5%	93%	96%	93%	93%	92%	93%	83%	100%	92%	93%	93%	93%	92%	93%	92%	96%	78%	81%	92%	77%	86%
64.4%	60%	72%	72%	63%	57%	83%	59%	59%	60%	68%	72%	60%	60%	70%	58%	59%	58%	48%	73%	64%	77%
80.8%	81%	86%	70%	75%	91%	81%	81%	75%	86%	81%	75%	81%	81%	81%	83%	81%	81%	74%	86%	83%	83%
53.8%	56%	59%	56%	47%	35%	63%	51%	54%	47%	50%	61%	65%	55%	62%	49%	53%	50%	52%	68%	50%	47%
79.6%	89%	82%	80%	76%	79%	67%	75%	75%	75%	79%	84%	81%	86%	86%	83%	79%	82%	77%	79%	79%	79%
79.6%	78%	83%	84%	84%	71%	74%	71%	66%	74%	68%	92%	71%	84%	88%	80%	84%	81%	92%	84%	81%	81%

Model Similarity Dendrogram

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