	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	1st 81.8%	9th 75.3%	6th 78.1%	2nd 81.1%	5th 78.5%	21st 57.4%	11th 73.1%	8th 75.3%	14th 72.1%	7th 77.7%	13th 72.7%	18th 67.7%	12th 72.9%	17th 70.2%	3rd 80.3%	4th 79.2%	15th 72.1%	10th 74.3%	20th 65.8%	16th 71.6%	19th 66.9%
75.6%	93%	81%	93%	93%	77%	53%	70%	66%	61%	82%	73%	71%	74%	58%	82%	90%	79%	90%	64%	72%	65%
74.7%	82%	76%	86%	84%	74%	92%	72%	82%	66%	70%	83%	80%	80%	84%	76%	72%	49%	49%	81%	76%	55%
79.1%	89%	74%	89%	89%	77%	10%	74%	97%	77%	95%	89%	77%	83%	81%	80%	82%	80%	81%	71%	75%	91%
86.2%	87%	84%	88%	85%	89%	88%	89%	91%	86%	89%	89%	87%	89%	89%	88%	87%	80%	82%	83%	89%	71%
82.0%	87%	87%	70%	74%	87%	72%	75%	81%	80%	84%	80%	88%	87%	80%	96%	79%	84%	90%	75%	71%	96%
65.4%	76%	66%	71%	72%	74%	64%	62%	64%	64%	73%	67%	46%	66%	56%	69%	74%	57%	64%	63%	55%	71%
65.9%	76%	57%	73%	91%	76%	46%	64%	75%	80%	65%	60%	46%	49%	71%	69%	74%	83%	64%	49%	59%	57%
71.1%	82%	70%	66%	86%	86%	36%	64%	84%	77%	83%	59%	69%	74%	55%	86%	90%	80%	77%	47%	61%	62%
67.9%	77%	81%	69%	81%	73%	37%	51%	69%	54%	81%	75%	41%	73%	68%	85%	84%	76%	75%	52%	62%	62%
82.4%	85%	86%	82%	88%	86%	97%	82%	76%	78%	86%	83%	86%	83%	78%	83%	79%	70%	84%	86%	63%	89%
78.3%	84%	92%	77%	83%	76%	85%	86%	88%	83%	68%	86%	86%	73%	71%	78%	85%	72%	76%	66%		52%
85.7%	93%	89%	89%	93%	89%	89%	84%	92%	82%	90%	80%	91%	80%	87%	91%	89%	76%	77%	80%	70%	89%
77.4%	89%	74%	86%	89%	74%	56%	89%	85%	75%	84%	68%	87%	78%	80%	84%	85%	73%	74%	59%	80%	56%
76.9%	82%	81%	80%	84%	74%	63%	88%	84%	86%	77%	77%	62%	64%	92%	81%	81%	77%	77%	71%	71%	63%
81.9%	81%	93%	81%	67%	84%	89%	74%	68%	75%	85%	93%	67%	80%	87%	91%	93%	90%	76%	85%	84%	76%
71.9%	94%	82%	83%	90%	85%	39%	67%	72%	77%	87%	64%	61%	76%	44%	92%	85%	74%	68%	54%	60%	55%
59.5%	61%	79%	88%	65%	84%	48%	59%	47%	47%	67%	59%	43%	46%	46%	70%	58%	42%	59%	62%
61.6%	80%	52%	75%	79%	82%	33%	47%	68%	47%	67%	44%	41%	58%	44%	69%	64%	90%	82%	53%	51%	68%
67.4%	77%	62%	69%	65%	72%	53%	86%	67%	67%	63%	76%	61%	64%	64%	77%	82%	69%	65%	53%	68%	56%
68.0%	77%	45%	71%	82%	73%	58%	66%	80%	73%	81%	64%	51%	60%	63%	76%	76%	50%	87%	61%	69%	64%
78.2%	90%	79%	79%	91%	80%	54%	76%	92%	74%	89%	71%	81%	66%	58%	83%	88%	90%	81%	58%	75%	87%
79.9%	89%	77%	79%	90%	82%	71%	83%	82%	76%	90%	71%	88%	79%	73%	91%	90%	80%	90%	57%	85%	55%
73.9%	72%	67%	69%	73%	79%	89%	81%	88%	69%	69%	85%	59%	73%	89%	73%	71%	71%	65%	66%	73%	70%
77.6%	90%	70%	83%	88%	84%	71%	85%	83%	80%	84%	71%	77%	80%	82%	84%	84%	68%	71%	58%	78%	59%
74.3%	80%	77%	79%	74%	65%	67%	82%	76%	79%	65%	80%	80%	66%	83%	71%	75%	77%	79%	83%	80%	42%
72.9%	76%	71%	78%	68%	82%	60%	70%	71%	76%	71%	70%	80%	75%	76%	71%	78%	66%	81%	73%	76%	62%
65.3%	84%	65%	80%	84%	80%	35%	51%	62%	62%	78%	39%	62%	69%	43%	80%	74%	73%	78%	52%	66%	55%
77.1%	85%	78%	73%	88%	85%	48%	85%	83%	83%	87%	72%	81%	82%	57%	88%	91%	87%	67%	56%	79%	65%
69.2%	84%	85%	86%	86%	84%	63%	69%	62%	62%	61%	62%	59%	70%	62%	65%	68%	63%	65%	61%	66%	71%
60.0%	69%	62%	58%	76%	81%	45%	44%	66%	60%	70%	70%	40%	65%	55%	77%	62%	40%	26%	52%	70%	72%
74.3%	77%	77%	80%	69%	72%	79%	73%	63%	71%	60%	83%	70%	74%	82%	74%	77%	79%	86%	80%	77%	57%
73.7%	71%	86%	71%	71%	83%	10%	86%	64%	83%	65%	71%	83%	76%	79%	85%	77%	80%	79%	89%	85%	53%
65.6%	73%	62%	76%	76%	64%	10%	62%	83%	64%	81%	76%	64%	70%	68%	62%	69%	67%	68%	59%	62%	62%
70.9%	86%	66%	75%	92%	92%	60%	76%	68%	70%	85%	75%	39%	60%	55%	88%	89%	73%	82%	52%	51%	54%
60.0%	83%	72%	68%	87%	24%	51%	42%	45%	65%	82%	47%	32%	68%	56%	52%	53%	37%	66%	84%	64%	82%
72.8%	86%	68%	82%	88%	81%	54%	80%	84%	65%	87%	74%	61%	76%	53%	86%	79%	78%	64%	53%	69%	61%
82.9%	88%	85%	87%	73%	89%	85%	80%	65%	83%	64%	90%	75%	81%	90%	95%	80%	86%	84%	85%	87%	89%
82.4%	89%	91%	88%	82%	84%	80%	79%	89%	77%	89%	84%	84%	81%	82%	95%	92%	78%	75%	93%	78%	41%
82.3%	94%	71%	89%	93%	89%	67%	88%	90%	82%	86%	76%	86%	82%	78%	94%	82%	87%	80%	68%	80%	66%
90.0%	96%	92%	93%	93%	94%	10%	92%	86%	94%	88%	93%	94%	99%	99%	98%	100%	97%	99%	88%	92%	92%
72.5%	69%	69%	71%	77%	79%	50%	80%	80%	81%	79%	72%	54%	72%	67%	79%	76%	55%	70%	70%	84%	88%
69.6%	74%	72%	67%	69%	73%	57%	71%	75%	63%	75%	61%	61%	71%	73%	70%	71%	70%	63%	78%	70%	78%
56.9%	60%	84%	61%	61%	57%	46%	58%	45%	48%	61%	64%	61%	61%	61%	67%	69%	48%	78%	0%	52%	52%

Model Similarity Dendrogram

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