	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	4th 72.8%	10th 70.4%	2nd 73.5%	3rd 73.3%	18th 67.8%	20th 65.1%	6th 71.9%	12th 70.0%	11th 70.4%	8th 71.2%	9th 71.1%	21st 63.7%	5th 72.2%	19th 66.2%	7th 71.7%	1st 73.6%	13th 69.8%	17th 68.7%	14th 69.6%	15th 69.2%	16th 69.1%
79.5%	81%	84%	91%	87%	68%	88%	88%	77%	91%	77%	84%	71%	84%	68%	76%	84%	70%	61%	85%	87%	68%
62.0%	71%	61%	67%	61%	47%	56%	65%	71%	71%	61%	56%	46%	60%	52%	68%	63%	63%	65%	71%	60%	66%
75.2%	68%	68%	59%	73%	89%	89%	66%	66%	59%	68%	89%	89%	89%	89%	68%	68%	68%	89%	89%	68%	68%
85.9%	89%	100%	89%	93%	80%	80%	100%	88%	89%	78%	80%	80%	80%	77%	77%	89%	85%	100%	80%	80%	89%
65.5%	67%	56%	61%	72%	56%	56%	71%	86%	78%	75%	56%	56%	56%	56%	72%	75%	67%	56%	56%	56%	92%
64.0%	75%	75%	64%	62%	75%	64%	57%	68%	68%	62%	62%	68%	68%	63%	53%	63%	71%	44%	51%	52%	79%
63.6%	67%	58%	68%	67%	54%	72%	52%	62%	67%	56%	52%	79%	63%	54%	69%	69%	76%	75%	58%	52%	65%
61.3%	64%	56%	70%	70%	58%	56%	56%	68%	56%	58%	64%	53%	58%	54%	73%	79%	70%	47%	68%	51%	59%
74.2%	69%	73%	70%	70%	83%	56%	71%	91%	78%	72%	81%	43%	91%	72%	83%	80%	78%	87%	67%	71%	72%
72.9%	80%	80%	69%	71%	80%	80%	72%	54%	64%	68%	80%	67%	80%	80%	77%	70%	71%	58%	80%	80%	69%
65.3%	74%	70%	82%	76%	53%	67%	68%	67%	71%	53%	75%	74%	53%	61%	58%	74%	51%	47%	68%	77%	52%
65.3%	65%	67%	73%	65%	66%	63%	74%	70%	73%	65%	60%	55%	67%	55%	73%	73%	66%	66%	55%	65%	55%
68.0%	67%	65%	76%	82%	69%	55%	76%	74%	65%	70%	65%	65%	67%	65%	69%	69%	65%	70%	65%	65%	65%
72.9%	76%	84%	79%	76%	68%	63%	73%	66%	76%	66%	76%	58%	76%	76%	80%	72%	69%	69%	76%	76%	76%
87.9%	91%	100%	100%	90%	79%	83%	100%	83%	88%	87%	100%	91%	91%	91%	78%	80%	79%	79%	88%	88%	79%
67.9%	76%	59%	72%	65%	75%	59%	59%	73%	67%	67%	60%	49%	74%	60%	67%	68%	70%	84%	65%	79%	77%
69.3%	63%	80%	80%	80%	89%	56%	63%	49%	64%	70%	75%	60%	55%	62%	82%	69%	70%	72%	58%		89%
69.8%	79%	62%	76%	67%	75%	52%	62%	68%	62%	68%	67%	66%	79%	48%	79%	82%	83%	91%	62%	75%	63%
54.4%	57%	40%	50%	48%	41%	40%	61%	51%	54%	57%	47%	51%	56%	51%	61%	63%	69%	72%	47%	69%	57%
77.0%	89%	75%	84%	87%	83%	74%	75%	78%	87%	83%	70%	67%	87%	68%	61%	65%	86%	79%	58%	82%	78%
71.8%	77%	71%	73%	73%	75%	71%	69%	77%	69%	75%	75%	75%	75%	75%	76%	71%	62%	72%	70%	66%	61%
73.9%	73%	75%	76%	73%	63%	78%	77%	83%	78%	75%	73%	64%	83%	77%	75%	75%	76%	69%	70%	55%	83%
72.6%	68%	78%	78%	68%	68%	79%	68%	79%	78%	80%	71%	49%	82%	71%	82%	88%	68%	77%	71%	49%	72%
67.5%	68%	68%	68%	80%	65%	60%	77%	70%	68%	62%	65%	65%	65%	65%	65%	83%	71%	65%	82%	65%	41%
75.8%	78%	75%	75%	90%	76%	72%	90%	74%	72%	76%	76%	66%	70%	76%	75%	79%	70%	67%	83%	77%	75%
78.7%	71%	83%	77%	73%	77%	70%	88%	66%	71%	81%	86%	88%	88%	88%	89%	88%	63%	63%	86%	79%	78%
74.0%	71%	79%	71%	76%	70%	90%	76%	71%	71%	89%	88%	88%	70%	77%	64%	76%	64%	47%	83%	69%	64%
52.7%	60%	46%	56%	56%	91%	36%	58%	60%	63%	54%	49%	32%	54%	32%	61%	62%	54%	54%	41%	41%	46%
64.1%	71%	70%	70%	70%	66%	58%	71%	64%	64%	58%	71%	49%	49%	69%	64%	64%	49%	64%	61%	67%	78%
60.1%	78%	55%	71%	77%	58%	45%	52%	63%	74%	69%	55%	36%	68%	45%	71%	65%	67%	58%	53%	54%	48%
72.5%	72%	79%	68%	75%	70%	66%	79%	79%	70%	68%	72%	64%	70%	70%	76%	76%	70%	70%	79%	74%	76%
39.3%	38%	38%	37%	38%	41%	41%	41%	37%	41%	38%	41%	41%	41%	41%	41%	38%	38%	34%	41%	41%	38%
82.9%	81%	81%	91%	76%	41%	100%	76%	76%	69%	81%	100%	84%	100%	89%	81%	81%	84%	69%	100%	100%	81%
71.9%	67%	62%	65%	67%	67%	70%	72%	67%	78%	78%	72%	72%	78%	76%	72%	76%	77%	72%	62%	76%	83%
59.6%	71%	78%	78%	71%	30%	64%	48%	55%	53%	52%	48%	61%	52%	51%	65%	74%	57%	72%	72%	51%	48%
64.1%	66%	67%	65%	62%	35%	63%	68%	69%	61%	92%	67%	52%	69%	50%	66%	61%	73%	65%	67%		65%
77.0%	83%	77%	83%	82%	83%	83%	83%	69%	83%	83%	70%	70%	74%	70%	80%	78%	72%	66%	78%	73%	78%
72.6%	72%	73%	80%	80%	92%	63%	89%	68%	76%	66%	80%	56%	80%	56%	75%	72%	68%	61%	56%	73%	89%
61.7%	67%	55%	72%	63%	70%	51%	62%	67%	55%	79%	64%	49%	70%	58%	67%	67%	49%	62%	46%	67%	55%
88.2%	100%	92%	91%	91%	100%	41%	100%	76%	69%	81%	100%	84%	100%	100%	81%	84%	81%	100%	100%	100%	81%
77.5%	90%	66%	87%	87%	70%	52%	82%	82%	80%	91%	70%	52%	77%	45%	90%	90%	90%	80%	73%	90%	83%
72.8%	68%	66%	67%	80%	75%	58%	79%	72%	72%	80%	76%	68%	75%	85%	72%	73%	73%	67%	79%	69%	74%
80.3%	71%	82%	82%	83%	46%	79%	78%	78%	83%	91%	89%	87%	82%	79%	70%	87%	98%	91%	93%		58%

Model Similarity Dendrogram

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