	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 76.9%	3rd 77.1%	7th 76.5%	2nd 77.8%	14th 74.0%	19th 71.0%	12th 75.4%	9th 75.7%	11th 75.4%	13th 74.3%	1st 77.8%	16th 72.9%	8th 76.3%	10th 75.5%	6th 76.8%	4th 76.9%	17th 72.1%	21st 68.4%	15th 73.5%	18th 71.7%	20th 70.6%
81.2%	88%	87%	79%	85%	71%	69%	76%	87%	80%	79%	86%	83%	86%	83%	81%	89%	79%	73%	82%	80%	83%
71.4%	70%	63%	74%	78%	57%	73%	67%	67%	60%	81%	73%	61%	82%	75%	81%	84%	79%	61%	78%	68%	68%
56.1%	57%	61%	61%	61%	44%	57%	47%	57%	47%	57%	59%	65%	57%	53%	58%	54%	57%	44%	47%	57%	78%
80.8%	86%	82%	82%	82%	80%	77%	73%	86%	80%	83%	82%	82%	79%	71%	83%	83%	82%	90%	72%	82%	80%
85.7%	84%	85%	84%	84%	95%	76%	86%	91%	95%	86%	87%	82%	88%	87%	81%	88%	94%	88%	86%	73%	79%
85.5%	88%	84%	79%	91%	93%	85%	84%	94%	88%	84%	94%	77%	84%	83%	88%	86%	84%	87%	85%	77%	80%
81.7%	76%	81%	83%	86%	82%	85%	90%	81%	81%	76%	82%	81%	82%	85%	82%	87%	80%	84%	78%	78%	75%
72.8%	75%	76%	77%	75%	70%	52%	83%	73%	82%	79%	74%	77%	66%	74%	73%	81%	67%	68%	52%	77%	78%
71.6%	80%	69%	64%	66%	82%	53%	63%	63%	66%	79%	74%	77%	80%	76%	71%	71%	82%	82%	64%	71%	71%
81.4%	83%	86%	79%	83%	82%	74%	85%	83%	79%	85%	85%	84%	85%	84%	84%	79%	71%	78%	81%	73%	87%
67.8%	74%	77%	79%	79%	66%	83%	70%	85%	73%	52%	72%	59%	58%	54%	79%	67%	66%	33%	84%	75%	38%
72.1%	73%	74%	73%	82%	76%	76%	69%	74%	69%	72%	73%	68%	73%	73%	73%	65%	68%	65%	78%	72%	69%
74.1%	77%	80%	79%	80%	81%	68%	74%	76%	83%	76%	77%	73%	78%	78%	82%	76%	75%	61%	73%	69%	41%
74.6%	75%	79%	68%	76%	79%	72%	78%	69%	75%	67%	73%	78%	75%	78%	71%	79%	71%	84%	83%	73%	63%
75.4%	82%	79%	80%	79%	77%	74%	77%	74%	75%	82%	81%	71%	74%	75%	75%	81%	75%	70%	73%	68%	62%
83.9%	82%	81%	86%	77%	74%	85%	89%	81%	88%	89%	88%	92%	86%	91%	85%	88%	80%	85%	87%	73%	74%
77.3%	79%	75%	63%	81%	85%	76%	82%	85%	77%	78%	87%	75%	77%	77%	81%	81%	67%	62%	77%	77%	81%
61.5%	72%	67%	64%	69%	68%	35%	64%	67%	66%	61%	46%	59%	61%	54%	67%	72%	51%	58%	53%	60%	77%
45.5%	50%	32%	50%	44%	52%	47%	47%	50%	39%	48%	38%	38%	48%	45%	65%	64%	40%	39%	37%	47%	35%
72.8%	73%	62%	66%	66%	76%	80%	74%	79%	88%	77%	69%	74%	78%	70%	70%	64%	76%	68%	69%	70%	80%
74.2%	82%	74%	95%	92%	77%	66%	82%	61%	73%	82%	78%	65%	79%	71%	74%	77%	74%	57%	59%	71%	70%
69.6%	76%	75%	74%	70%	78%	66%	75%	75%	71%	72%	72%	66%	71%	72%	70%	72%	65%	53%	54%	74%	60%
54.1%	51%	56%	54%	56%	72%	73%	60%	65%	53%	10%	64%	44%	56%	63%	49%	52%	50%	50%	55%	55%	49%
73.2%	78%	83%	82%	83%	70%	91%	68%	72%	75%	84%	78%	54%	75%	72%	82%	75%	71%	69%	83%	58%	34%
83.5%	80%	90%	81%	84%	88%	84%	82%	82%	83%	78%	87%	90%	87%	90%		82%	77%	90%	88%	78%	68%
74.2%	79%	79%	85%	80%	79%	68%	83%	76%	75%	82%	86%	73%	76%	67%	75%	73%	54%	64%	73%	71%	61%
67.4%	81%	71%	73%	79%	63%	38%	63%	68%	63%	72%	53%	70%	70%	64%	79%	74%	77%	52%	64%	66%	76%
74.3%	72%	79%	77%	76%	65%	56%	72%	78%	80%	74%	77%	77%	79%	73%	74%	74%	78%	81%	69%	76%	74%
66.0%	78%	86%	79%	78%	72%	59%	86%	70%	68%	49%	79%	44%	54%	57%	68%	68%	47%	46%	75%	60%	62%
74.7%	77%	84%	77%	80%	77%	63%	61%	77%	74%	71%	82%	69%	78%	79%	80%	71%	71%	69%	78%	81%	69%
76.5%	75%	73%	79%	79%	77%	81%	76%	70%	82%	75%	82%	90%	87%	82%	73%	84%	78%	69%	84%	58%	53%
88.1%	86%	83%	82%	82%	98%	86%	98%	86%	98%	86%	85%	78%	86%	91%	91%	91%	86%	98%	98%	63%	98%
69.4%	66%	73%	74%	74%	55%	70%	59%	70%	59%	70%	71%	78%	70%	65%	66%	66%	70%	55%	59%	94%	94%
77.4%	83%	84%	71%	76%	84%	74%	80%	80%	90%	69%	78%	71%	66%	73%	75%	82%	82%	77%	64%	83%	83%
77.0%	83%	82%	90%	90%	49%	79%	76%	85%	80%	82%	90%	82%	82%	80%	68%	63%	77%	75%	66%	63%	74%
64.1%	70%	65%	68%	77%	52%	60%	68%	71%	64%	72%	68%	61%	67%	61%	72%	62%	60%	49%	55%	66%	58%
80.1%	83%	82%	85%	78%	90%	88%	83%	75%	86%	85%	83%	77%	90%	84%	86%	83%	70%	59%	89%	69%	58%
81.7%	90%	87%	85%	83%	88%	81%	83%	84%	92%	85%	89%	75%	90%	88%	78%	80%	63%	72%	83%	56%	83%
82.7%	80%	83%	98%	92%	73%	80%	85%	76%	85%	88%	95%	90%	90%	84%	96%	95%	67%	52%	77%	84%	67%
93.8%	96%	92%	91%	91%	89%	96%	92%	96%	92%	96%	94%	87%	96%	99%	95%	100%	96%	89%	92%	95%	96%
74.4%	70%	79%	74%	76%	63%	66%	75%	75%	70%	73%	75%	81%	73%	78%	76%	85%	78%	76%	76%	70%	73%
78.2%	83%	88%	70%	72%	74%	60%	79%	75%	67%	70%	88%	70%	83%	94%	83%	74%	80%	81%	88%	79%	85%
80.0%	64%	88%	74%	73%	61%	69%	77%	66%	73%	79%	92%	85%	77%	93%	87%	85%	84%	77%	94%	91%	91%

Model Similarity Dendrogram

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