	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	6th 72.7%	3rd 73.2%	1st 73.7%	5th 73.1%	21st 61.0%	19th 63.7%	8th 72.0%	2nd 73.3%	9th 71.4%	11th 70.8%	10th 70.9%	13th 70.0%	12th 70.2%	15th 69.3%	7th 72.3%	4th 73.2%	14th 69.4%	16th 68.2%	18th 64.3%	20th 63.3%	17th 65.1%
74.4%	67%	84%	82%	75%	46%	62%	77%	87%	81%	77%	81%	77%	70%	87%	82%	85%	62%	84%	73%	60%	63%
77.1%	76%	85%	78%	73%	45%	83%	80%	87%	70%	70%	81%	83%	92%	86%	72%	70%	92%	86%	79%	59%	72%
82.8%	86%	84%	86%	93%	86%	89%	81%	86%	70%	93%	86%	86%	75%	91%	81%	81%	93%	86%	86%	44%	75%
66.2%	68%	73%	65%	65%	73%	57%	73%	57%	62%	67%	73%	73%	68%	54%	66%	71%	69%	62%	48%	73%	73%
80.4%	82%	92%	71%	71%	78%	61%	67%	87%	83%	100%	92%	69%	78%	88%	80%	89%	90%	99%	67%	89%	55%
77.9%	69%	78%	71%	80%	86%	77%	86%	86%	77%	77%	70%	77%	86%	73%	69%	75%	81%	76%	80%	73%	88%
68.2%	76%	73%	71%	64%	53%	71%	75%	77%	77%	70%	57%	76%	54%	76%	68%	70%	78%	78%	66%	47%	55%
78.8%	91%	80%	82%	76%	60%	62%	79%	93%	87%	72%	80%	88%	66%	76%	79%	97%	87%	80%	63%		77%
79.9%	67%	79%	93%	83%	55%	62%	73%	93%	76%	83%	83%	81%	94%	76%	76%	79%	88%	81%	78%	88%	89%
82.3%	87%	91%	82%	100%	73%	84%	91%	76%	80%	88%	88%	73%	91%	76%	76%	80%	82%	75%	76%	69%	91%
80.1%	86%	92%	87%	79%	67%	83%	81%	77%	83%	66%	88%	88%	80%	80%	81%	88%	75%	67%	76%		77%
66.7%	69%	67%	67%	74%	69%	63%	67%	67%	67%	67%	67%	82%	61%	59%	68%	68%	66%	62%	59%	69%	63%
75.8%	67%	86%	81%	71%	40%	76%	75%	76%	76%	89%	89%	63%	89%	77%	73%	80%	80%	75%	70%	82%	76%
67.8%	59%	85%	79%	59%	49%	70%	92%	74%	79%	55%	82%	89%	48%	89%	57%	82%	61%	81%	52%	41%	41%
70.2%	73%	64%	75%	80%	55%	61%	79%	83%	79%	68%	54%	90%	75%	70%	71%	60%	86%	65%	54%	74%	58%
59.9%	60%	65%	73%	71%	56%	48%	59%	67%	67%	61%	46%	60%	66%	51%	60%	58%	63%	63%	50%	51%	63%
55.1%	73%	60%	82%	64%	70%	35%	60%	38%	58%	45%	60%	45%	42%	52%	58%	56%	52%	37%	54%	63%	54%
68.4%	82%	65%	72%	86%	69%	42%	46%	79%	60%	78%	52%	61%	83%	57%	90%	74%	77%	73%	56%	52%	82%
43.2%	44%	29%	52%	40%	49%	33%	42%	48%	40%	38%	42%	19%	50%	41%	63%	77%	37%	34%	33%	44%	52%
69.0%	74%	50%	72%	76%	77%	68%	67%	82%	71%	73%	52%	74%	75%	67%	75%	72%	80%	63%	67%	57%	57%
74.3%	78%	88%	88%	69%	48%	75%	90%	71%	79%	72%	80%	85%	88%	78%	75%	81%	46%	65%	54%	79%	71%
71.2%	58%	77%	83%	67%	45%	62%	82%	75%	82%	71%	69%	75%	83%	76%	61%	80%	79%	75%	62%	75%	58%
67.1%	57%	68%	65%	65%	59%	80%	76%	82%	68%	67%	67%	63%	68%	94%	68%	69%	67%	53%	68%	53%	53%
70.0%	70%	81%	74%	66%	53%	79%	71%	67%	73%	85%	79%	30%	73%	72%	74%	75%	75%	50%	78%	72%	73%
58.0%	63%	61%	58%	61%	46%	65%	63%	63%	61%	48%	67%	63%	48%	63%	57%	59%	49%	62%	61%	47%	53%
57.4%	55%	61%	57%	52%	43%	53%	54%	66%	63%	48%	62%	60%	57%	71%	42%	56%	48%	76%	63%	71%	47%
60.8%	71%	67%	71%	71%	57%	47%	46%	66%	52%	67%	51%	68%	67%	46%	70%	68%	68%	65%	60%	63%	35%
54.7%	82%	53%	52%	74%	83%	38%	65%	54%	65%	65%	44%	49%	49%	38%	57%	57%	37%	44%	27%	58%	58%
62.7%	73%	71%	71%	80%	63%	55%	67%	59%	68%	56%	61%	59%	52%	59%	71%	61%	56%	56%	59%	61%	58%
75.5%	77%	78%	79%	87%	72%	52%	78%	77%	70%	76%	92%	92%	80%	53%	84%	69%	88%	81%	89%	56%	56%
75.9%	93%	76%	82%	86%	90%	68%	87%	81%	76%	86%	60%	84%	61%	71%	87%	86%	64%	71%	67%	57%	60%
68.8%	67%	70%	67%	61%	67%	65%	73%	67%	84%	61%	67%	67%	79%	63%	79%	67%	61%	67%	67%	79%	67%
61.9%	63%	61%	63%	68%	63%	65%	58%	63%	49%	68%	63%	63%	53%	67%	53%	58%	68%	63%	63%	74%	53%
80.9%	88%	90%	84%	80%	61%	81%	84%	86%	92%	75%	84%	85%	88%	78%	93%	88%	82%	88%	65%	44%	82%
62.0%	67%	66%	67%	57%	26%	65%	64%	53%	67%	72%	68%	53%	67%	65%	71%	54%	53%	72%	65%	67%	64%
71.4%	82%	80%	69%	93%	40%	59%	82%	76%	82%	83%	76%	69%	73%	63%	86%	84%	67%	53%	59%	44%	79%
69.6%	75%	71%	76%	83%	64%	62%	78%	78%	75%	60%	57%	84%	71%	71%	71%	72%	61%	68%	57%	70%	57%
79.7%	73%	86%	78%	78%	69%	72%	73%	84%	78%	78%	93%	86%	84%	88%	86%	88%	86%	77%	77%	66%	73%
56.5%	72%	57%	72%	72%	25%	54%	64%	72%	55%	72%	53%	60%	56%	45%	73%	62%	49%	38%	47%	40%	48%
95.4%	100%	98%	100%	94%	100%	97%	94%	100%	83%	94%	100%	100%	89%	95%	94%	94%	94%	100%	100%	89%	89%
71.6%	76%	66%	70%	68%	77%	59%	77%	80%	81%	72%	94%	45%	74%	67%	75%	75%	61%	67%	67%	76%	77%
54.9%	60%	56%	54%	58%	43%	42%	54%	54%	55%	60%	58%	62%	54%	55%	61%	57%	57%	46%	54%	53%	60%
69.1%	70%	82%	68%	74%	74%	59%	67%	56%	70%	72%	82%	56%	63%	74%	74%	74%	69%	67%	68%	66%	67%

Model Similarity Dendrogram

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