	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
Score	5th 64.8%	9th 64.0%	1st 67.1%	17th 60.7%	21st 59.0%	16th 60.7%	14th 61.5%	11th 62.6%	15th 61.0%	2nd 66.0%	6th 64.5%	19th 59.9%	7th 64.5%	8th 64.0%	3rd 65.5%	4th 65.3%	13th 61.7%	20th 59.7%	10th 63.1%	12th 61.8%	18th 60.0%
69.8%	75%	66%	74%	75%	74%	61%	72%	72%	66%	90%	64%	47%	90%	72%	68%	68%	66%	53%	72%	64%	77%
49.3%	48%	46%	57%	60%	18%	54%	50%	49%	43%	50%	58%	56%	50%	56%	57%	61%	50%	36%	51%	43%	43%
48.5%	51%	50%	63%	0%	44%	55%	51%	56%	44%	51%	59%	48%	44%	59%	51%	51%	51%	44%	51%	51%	44%
62.0%	54%	69%	62%	51%	58%	68%	66%	65%	62%	66%	58%	58%	66%	66%	65%	60%	68%	68%	55%	58%	58%
75.6%	66%	77%	66%	78%	82%	65%	66%	87%	87%	77%	77%	80%	83%	78%	66%	75%	79%	67%	78%	77%	77%
73.1%	67%	66%	64%	67%	77%	77%	77%	72%	77%	72%	77%	79%	77%	77%	66%	67%	86%	70%	70%	84%	67%
69.8%	68%	75%	74%	74%	63%	69%	67%	66%	65%	67%	67%	75%	75%	63%	71%	70%	70%	75%	64%	73%	74%
50.9%	54%	54%	54%	54%	27%	33%	51%	42%	48%	67%	51%	47%	51%	51%	56%	53%	54%	46%	37%	44%	95%
65.8%	75%	66%	53%	53%	63%	41%	54%	87%	58%	75%	64%	63%	75%	75%	68%	70%	73%	67%	53%	75%	74%
58.5%	55%	55%	55%	55%	58%	60%	55%	60%	58%	71%	58%	58%	58%	58%	61%	65%	53%	61%	58%	58%	58%
53.6%	58%	66%	58%	58%	23%	64%	58%	67%	59%	51%	51%	58%	44%	59%	59%	55%	51%	28%	64%	58%	36%
56.1%	58%	67%	49%	55%	47%	65%	57%	61%	58%	46%	57%	68%	46%	57%	58%	71%	37%	58%	61%	53%	50%
60.4%	67%	61%	87%	75%	67%	72%	62%	51%	65%	63%	74%	65%	67%	74%	49%	50%	54%	35%	64%	33%	33%
57.2%	58%	55%	55%	64%	58%	55%	51%	54%	63%	56%	63%	61%	63%	51%	64%	62%	55%	52%	57%	57%	48%
59.7%	74%	59%	57%	68%	55%	64%	54%	41%	47%	65%	74%	41%	63%	64%	66%	62%	57%	64%	70%	39%	70%
65.2%	64%	61%	70%	62%	56%	61%	75%	64%	58%	86%	75%	47%	64%	71%	70%	74%	57%	56%	67%	58%	74%
73.4%	74%	82%	96%	86%	85%	63%	74%	48%	70%	70%	80%	62%	74%	74%	82%	82%	75%	72%	79%	83%	30%
66.4%	66%	58%	66%	74%	85%	45%	53%	64%	63%	54%	55%	87%	71%	58%	69%	69%	72%	62%	64%	74%	85%
50.9%	47%	39%	57%	48%	51%	42%	57%	60%	57%	67%	50%	33%	60%	57%	54%	54%	44%	51%	39%	44%	57%
62.9%	57%	55%	58%	58%	58%	71%	55%	64%	64%	63%	69%	71%	67%	64%	57%	65%	60%	65%	63%	71%	66%
52.4%	57%	57%	58%	55%	55%	42%	58%	53%	55%	64%	55%	45%	45%	47%	52%	52%	42%	44%	43%	54%	68%
59.0%	64%	66%	77%	77%	0%	70%	62%	50%	59%	57%	74%	50%	58%	66%	60%	64%	72%	44%	70%	64%	36%
54.8%	69%	52%	56%	43%	73%	70%	64%	69%	56%	58%	43%	35%	63%	72%	52%	43%	39%	44%	64%	35%	50%
57.4%	74%	61%	69%	74%	68%	70%	55%	49%	71%	59%	65%	47%	61%	64%	61%	48%	48%	47%	51%	32%	32%
58.9%	64%	61%	65%	67%	64%	56%	62%	53%	54%	51%	58%	58%	58%	54%	68%	55%	54%	65%	62%	53%	54%
54.8%	60%	52%	58%	63%	43%	51%	52%	60%	54%	64%	56%	38%	58%	51%	56%	59%	49%	51%	58%	58%	59%
65.7%	71%	63%	68%	74%	74%	39%	57%	67%	58%	80%	55%	53%	90%	57%	77%	62%	63%	74%	64%	58%	75%
66.0%	73%	77%	75%	74%	53%	55%	65%	79%	62%	74%	62%	59%	62%	53%	80%	74%	72%	62%	61%	62%	53%
59.5%	59%	73%	78%	78%	61%	61%	61%	66%	61%	43%	59%	58%	43%	46%	66%	66%	56%	35%	64%	64%	52%
72.8%	64%	75%	75%	75%	92%	57%	54%	69%	57%	64%	69%	80%	76%	69%	75%	73%	77%	79%	90%	90%	68%
62.1%	64%	57%	62%	75%	75%	66%	47%	46%	47%	64%	64%	61%	58%	66%	63%	68%	51%	61%	69%	75%	66%
82.7%	82%	88%	73%	0%	95%	82%	87%	81%	95%	87%	78%	91%	95%	78%	78%	87%	87%	95%	87%	95%	95%
49.0%	51%	50%	63%	0%	44%	55%	51%	56%	44%	51%	59%	48%	44%	59%	51%	51%	51%	59%	51%	48%	44%
68.7%	67%	77%	75%	59%	43%	72%	70%	65%	71%	67%	67%	71%	75%	73%	70%	67%	71%	76%	72%	71%	64%
58.8%	63%	55%	63%	65%	37%	69%	42%	63%	42%	63%	63%	70%	63%	56%	63%	62%	56%	53%	63%	65%	58%
68.8%	77%	75%	77%	84%	49%	67%	71%	54%	63%	67%	67%	64%	67%	67%	77%	72%	70%	74%	65%	63%	74%
75.6%	79%	83%	75%	84%	82%	72%	62%	53%	60%	84%	79%	60%	73%	76%	87%	87%	84%	73%	76%		83%
82.8%	85%	81%	97%	90%	85%	97%	84%	90%	87%	84%	85%	77%	90%	85%	83%	95%	68%	85%	92%	68%	31%
59.6%	65%	52%	62%	63%	56%	48%	59%	58%	54%	85%	59%	54%	59%	51%	68%	63%	66%	55%	44%	62%	68%
67.2%	71%	70%	84%	0%	63%	75%	71%	77%	63%	71%	80%	67%	63%	80%	71%	71%	71%	63%	71%	67%	63%
72.4%	70%	69%	71%	70%	64%	59%	77%	82%	82%	78%	74%	74%	70%	67%	77%	84%	63%	67%	63%	86%	74%
60.1%	58%	67%	58%	54%	50%	37%	65%	65%	56%	54%	67%	56%	56%	73%	67%	64%	69%	67%	58%	63%	58%
59.9%	64%	62%	70%	70%	62%	57%	64%	58%	58%	64%	56%	55%	60%	56%	58%	56%	60%	62%	60%	64%	41%

Model Similarity Dendrogram

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