	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	5th 68.7%	9th 66.7%	1st 69.3%	2nd 69.2%	6th 67.5%	18th 61.9%	7th 67.5%	8th 67.3%	10th 66.5%	11th 66.2%	12th 65.4%	21st 61.3%	13th 65.3%	16th 62.1%	4th 68.8%	3rd 69.2%	19th 61.7%	17th 61.9%	14th 63.3%	20th 61.5%	15th 63.2%
77.4%	77%	77%	100%	100%	75%	67%	76%	77%	77%	76%	90%	39%	78%	73%	78%	79%	78%	72%	88%	71%	78%
65.8%	70%	60%	70%	73%	37%	73%	73%	56%	60%	67%	70%	64%	70%	67%	68%	72%	50%	60%	73%	61%	88%
45.4%	44%	41%	44%	44%	44%	41%	47%	47%	44%	47%	55%	54%	47%	54%	41%	47%	34%	44%	47%	47%	41%
64.8%	71%	57%	68%	71%	71%	55%	71%	71%	65%	71%	67%	70%	67%	52%	77%	68%	67%	52%	39%	70%	61%
71.1%	76%	70%	76%	76%	80%	71%	76%	70%	72%	79%	70%	64%	70%	70%	67%	70%	63%	66%	76%	66%	66%
85.9%	91%	82%	82%	82%	91%	82%	91%	68%	80%	87%	87%	87%	87%	87%	91%	96%	83%	85%	87%	87%	91%
66.8%	64%	60%	60%	64%	76%	57%	62%	79%	79%	57%	64%	68%	57%	65%	64%	76%	62%	90%	66%	79%	53%
70.4%	65%	61%	59%	59%	81%	62%	82%	82%	82%	82%	61%	55%	75%	67%	72%	78%	75%	77%	73%	63%	68%
84.0%	79%	82%	82%	82%	91%	69%	82%	82%	89%	91%	89%	79%	89%	79%	82%	89%	89%	82%	82%	83%	91%
73.0%	80%	70%	80%	80%	70%	70%	66%	72%	83%	70%	66%	70%	84%	70%	74%	79%	69%	70%	70%	70%	69%
46.0%	52%	48%	54%	54%	41%	60%	54%	60%	47%	39%	48%	54%	29%	45%	41%	40%	22%	60%	60%	49%	9%
71.6%	75%	78%	70%	76%	77%	70%	71%	74%	74%	58%	74%	70%	62%	74%	88%	71%	54%	70%	70%	74%	73%
78.7%	81%	76%	87%	75%	100%	81%	87%	87%	75%	87%	75%	63%	87%	100%	61%	84%	61%	76%	88%	61%	61%
71.5%	66%	74%	66%	74%	89%	61%	68%	90%	74%	74%	78%	56%	74%	58%	74%	74%	78%	68%	74%	68%	64%
75.9%	89%	89%	87%	81%	69%	77%	78%	74%	71%	79%	84%	89%	71%	69%	81%	89%	60%	75%	56%	71%	55%
69.7%	75%	68%	73%	75%	60%	56%	68%	70%	66%	91%	76%	45%	68%	76%	77%	69%	40%	74%	68%	68%	100%
60.7%	69%	76%	76%	58%	76%	56%	63%	50%	58%	49%	58%	69%	58%	58%	58%	76%	51%	50%	61%	52%	52%
55.1%	61%	54%	61%	61%	63%	32%	52%	64%	61%	46%	54%	68%	54%	38%	58%	51%	46%	58%	45%	75%	56%
38.6%	37%	20%	43%	37%	78%	22%	31%	50%	43%	50%	31%	22%	43%	20%	61%	54%	57%	29%	22%	50%	10%
53.6%	60%	67%	60%	60%	56%	49%	67%	47%	47%	60%	56%	39%	56%	39%	60%	52%	46%	46%	64%	39%	56%
60.8%	62%	66%	57%	54%	58%	62%	55%	60%	55%	66%	66%	73%	66%	65%	65%	66%	64%	51%	67%	46%	52%
75.4%	65%	73%	73%	73%	58%	82%	72%	62%	76%	78%	87%	87%	76%	73%	76%	77%	73%	71%	85%	85%	82%
58.5%	64%	62%	56%	64%	62%	55%	58%	63%	53%	62%	53%	60%	60%	65%	64%	60%	50%	56%	54%	53%	55%
76.0%	82%	75%	82%	82%	70%	78%	75%	75%	75%	75%	75%	60%	77%	74%	88%	67%	64%	75%	70%	88%	88%
68.4%	68%	64%	68%	68%	75%	62%	64%	77%	68%	68%	70%	67%	80%	68%	68%	71%	57%	65%	73%	62%	74%
61.8%	56%	66%	63%	60%	63%	89%	66%	50%	58%	60%	66%	74%	56%	66%	61%	56%	58%	59%	66%	52%	52%
59.9%	61%	59%	68%	68%	66%	46%	46%	68%	65%	54%	54%	50%	52%	54%	68%	60%	71%	57%	52%	59%	79%
40.4%	60%	41%	47%	60%	66%	19%	40%	52%	50%	41%	41%	27%	41%	27%	53%	53%	43%	20%	19%	10%	39%
71.7%	83%	100%	88%	100%	55%	63%	83%	74%	83%	63%	55%	63%	63%	66%	76%	73%	51%	55%	83%	55%	73%
74.5%	82%	70%	90%	90%	77%	66%	100%	77%	70%	71%	68%	65%	74%	63%	69%	76%	75%	69%	70%	71%	71%
50.1%	50%	50%	50%	45%	48%	48%	54%	51%	50%	50%	55%	55%	49%	54%	56%	58%	56%	43%	49%	35%	47%
87.3%	88%	92%	88%	88%	88%	92%	88%	85%	88%	85%	76%	77%	85%	77%	92%	93%	100%	90%	85%	85%	92%
45.1%	44%	41%	44%	44%	44%	41%	44%	47%	44%	47%	55%	54%	47%	54%	41%	40%	34%	47%	47%	47%	41%
55.9%	87%	49%	80%	87%	54%	38%	46%	56%	64%	65%	46%	39%	51%	46%	69%	69%	62%	39%	37%	39%	51%
58.1%	65%	65%	65%	65%	41%	68%	51%	70%	54%	62%	47%	63%	62%	47%	54%	65%	58%	59%	65%	47%	47%
58.9%	62%	61%	63%	70%	55%	51%	66%	61%	59%	64%	59%	53%	61%	53%	63%	61%	63%	41%	47%		65%
71.8%	71%	77%	76%	71%	76%	62%	83%	87%	76%	62%	73%	57%	70%	57%	87%	82%	79%	59%	57%	76%	70%
60.2%	65%	65%	65%	65%	69%	66%	69%	57%	61%	78%	60%	54%	65%	60%	65%	66%	52%	50%	60%	36%	36%
53.0%	61%	53%	50%	50%	49%	50%	57%	61%	61%	47%	53%	50%	53%	50%	58%	56%	53%	54%	37%	55%	55%
93.8%	96%	100%	96%	96%	96%	100%	96%	92%	96%	92%	83%	85%	92%	85%	100%	93%	92%	96%	92%	92%	100%
62.5%	60%	71%	60%	60%	66%	63%	67%	63%	63%	63%	61%	42%	63%	51%	63%	70%	69%	71%	54%	70%	63%
82.2%	84%	88%	83%	83%	76%	81%	90%	84%	84%	83%	82%	90%	83%	76%	84%	82%	78%	74%	75%		84%
63.3%	58%	68%	69%	52%	67%	68%	69%	52%	58%	52%	75%	68%	58%	78%	67%	66%	67%	57%	68%	54%	58%

Model Similarity Dendrogram

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