	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 67.9%	14th 63.5%	6th 67.7%	4th 68.2%	17th 62.5%	15th 63.0%	9th 65.4%	19th 60.0%	11th 64.0%	3rd 68.5%	10th 64.3%	21st 59.8%	13th 63.6%	16th 62.8%	1st 71.3%	2nd 69.6%	7th 67.0%	18th 60.2%	20th 60.0%	12th 63.7%	8th 65.9%
77.3%	75%	71%	90%	87%	75%	90%	100%	56%	64%	90%	100%	71%	75%	80%	75%	75%	68%	73%	75%	70%	64%
54.2%	49%	63%	48%	63%	28%	63%	58%	58%	46%	52%	54%	74%	52%	64%	53%	49%	49%	58%	58%	52%	48%
60.1%		65%	56%	56%	100%	76%	59%	56%	48%	65%	40%	48%	40%	76%	65%	65%	65%	40%	40%	76%	65%
60.7%	48%	69%	62%	51%	41%	73%	66%	58%	62%	66%	58%	58%	73%	66%	65%	50%	61%	62%	70%	58%	58%
68.3%	65%	66%	67%	67%	66%	66%	78%	77%	78%	66%	66%	66%	66%	66%	67%	77%	67%	64%	66%	66%	67%
72.8%	70%	61%	61%	61%	51%	88%	81%	75%	70%	77%	81%	75%	81%	84%	70%	78%	75%	79%	70%	70%	70%
74.5%	100%	71%	87%	90%	76%	72%	65%	58%	70%	68%	61%	67%	61%	67%	90%	100%	100%	66%	56%	67%	72%
55.5%	67%	55%	65%	64%	71%	45%	45%	48%	55%	65%	55%	31%	55%	24%	63%	54%	55%	63%	51%	63%	72%
59.4%	57%	55%	55%	55%	58%	50%	58%	75%	58%	68%	37%	37%	58%	68%	69%	68%	69%	57%	52%	68%	75%
58.4%	55%	55%	55%	54%	58%	58%	60%	60%	58%	53%	58%	58%	58%	58%	71%	75%	49%	60%	58%	58%	58%
51.1%		64%	71%	58%	56%	56%	58%	64%	63%	45%	65%	64%	48%	36%	59%	62%	39%	29%	39%	10%	36%
56.8%	58%	66%	49%	55%	47%	62%	57%	53%	58%	57%	57%	68%	39%	65%	71%	64%	53%	36%	62%	46%	69%
73.7%	89%	68%	89%	89%	68%	100%	68%	71%	68%	68%	75%	64%	75%	64%	89%	75%	71%	51%	77%	64%	64%
73.3%	80%	66%	64%	72%	80%	67%	64%	61%	66%	77%	80%	67%	66%	80%	67%	70%	87%	86%	80%	80%	79%
76.2%	75%	70%	80%	87%	70%	77%	87%	70%	70%	70%	70%	64%	87%	70%	100%	80%	71%	73%	70%	75%	85%
76.5%	71%	80%	80%	80%	66%	80%	90%	58%	80%	90%	100%	56%	71%	80%	73%	74%	62%	70%	80%	90%	76%
66.0%		80%	90%	90%	14%	64%	64%	55%	70%	70%	70%	61%	64%	70%	70%	79%	57%	44%	80%	70%	58%
61.6%	59%	53%	59%	59%	87%	58%	56%	59%	64%	58%	58%	64%	56%	59%	59%	57%	81%	78%	56%	58%	56%
51.8%	56%	39%	57%	39%	51%	44%	50%	45%	57%	71%	59%	29%	48%	57%	76%	61%	57%	35%	47%	65%	45%
57.3%	56%	45%	54%	54%	53%	71%	45%	51%	65%	64%	63%	71%	64%	71%	54%	58%	65%	41%	55%	71%	32%
44.3%	47%	42%	47%	47%	38%	38%	39%	54%	42%	47%	38%	37%	38%	38%	56%	49%	54%	45%	32%	38%	64%
72.1%	74%	75%	74%	74%	52%	75%	71%	65%	75%	75%	87%	64%	74%	89%	74%	75%	75%	54%	68%	75%	69%
58.2%	50%	50%	56%	49%	77%	72%	69%	69%	61%	67%	56%	35%	70%	61%	50%	53%	77%	49%	61%	39%	52%
65.9%	64%	61%	64%	64%	64%	64%	71%	69%	66%	64%	64%	64%	64%	64%	64%	74%	74%	72%	64%	64%	64%
72.4%	88%	70%	75%	75%	65%	62%	70%	63%	63%	80%	54%	70%	70%	80%	81%	83%	78%	67%	80%	80%	67%
62.3%	74%	58%	67%	67%	65%	61%	67%	54%	64%	67%	67%	51%	54%	65%	67%	61%	64%	59%	51%	59%	67%
71.0%	75%	61%	87%	80%	68%	70%	70%	58%	58%	75%	64%	75%	80%	65%	82%	87%	75%	70%	48%		71%
69.0%	87%	54%	67%	87%	76%	38%	68%	65%	71%	74%	76%	41%	74%	45%	87%	87%	87%	64%	54%	68%	79%
59.4%	66%	76%	78%	78%	66%	61%	61%	61%	57%	53%	35%	35%	35%	47%	78%	73%	45%	35%	66%	66%	76%
69.2%		65%	64%	64%	89%	55%	61%	72%	65%	65%	65%	72%	65%	65%	70%	72%	82%	74%	89%	65%	65%
75.6%	75%	89%	89%	89%	71%	71%	71%	10%	75%	74%	71%	85%	89%	71%	79%	79%	84%	81%	85%	71%	79%
52.3%		51%	51%	59%	59%	59%	57%	59%	81%	48%	51%	59%	40%	40%	48%	48%	48%	59%	40%	40%	48%
59.2%		65%	56%	56%	100%	76%	59%	56%	48%	65%	40%	48%	40%	76%	65%	65%	65%	40%	40%		65%
74.7%	65%	79%	79%	67%	56%	75%	79%	65%	79%	89%	71%	79%	75%	70%	75%	69%	65%	89%	79%	89%	75%
61.5%	71%	50%	63%	63%	37%	60%	47%	58%	63%	70%	70%	52%	71%	68%	65%	62%	64%	59%	63%	68%	68%
64.5%	84%	58%	84%	84%	61%	41%	44%	70%	70%	71%	75%	55%	71%	28%	84%	77%	58%	56%	44%	55%	84%
74.4%	73%	71%	75%	75%	71%	74%	75%	68%	71%	71%	71%	79%	71%	71%	88%	88%	88%	71%	70%	71%	71%
71.1%		76%	76%	76%	64%	66%	87%	59%	67%	87%	66%	70%	66%	66%	80%	84%	59%	62%	66%	75%	70%
57.0%	56%	56%	63%	56%	65%	39%	56%	51%	53%	87%	66%	77%	81%	51%	54%	48%	56%	57%	24%	41%	61%
73.3%		84%	82%	87%	59%	59%	80%	63%	59%	91%	59%	59%	76%	76%	91%	87%	87%	59%	59%	59%	91%
61.2%	64%	38%	54%	63%	72%	38%	80%	54%	64%	54%	90%	55%	69%	30%	76%	70%	64%	74%	30%	78%	69%
66.1%	65%	74%	65%	76%	56%	38%	65%	65%	56%	65%	74%	58%	65%	66%	74%	74%	73%	69%	65%	74%	71%
59.6%		66%	58%	66%	41%	55%	55%	65%	72%	66%	49%	58%	58%	63%	71%	58%	58%	58%	58%	58%	58%

Model Similarity Dendrogram

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