	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 83.6%	3rd 81.5%	6th 80.9%	2nd 82.2%	20th 69.2%	21st 68.9%	12th 75.2%	10th 77.1%	9th 77.2%	4th 81.1%	11th 76.0%	15th 73.4%	8th 78.8%	19th 72.4%	5th 81.0%	7th 80.6%	16th 73.1%	17th 73.0%	13th 73.9%	14th 73.6%	18th 72.6%
81.4%	97%	93%	94%	93%	78%	55%	71%	88%	86%	91%	72%	83%	94%	58%	83%	92%	83%	79%	72%	66%
73.0%	82%	72%	85%	85%	22%	84%	69%	86%	66%	74%	83%	78%	76%	86%	71%	76%	53%	65%	85%	80%	56%
76.1%	87%	83%	64%	89%	0%	80%	73%	75%	68%	89%	89%	77%	81%	83%	64%	76%	80%	81%	80%	86%	94%
86.2%	89%	83%	89%	86%	86%	80%	89%	86%	86%	89%	89%	86%	90%	79%	89%	89%	83%	85%	86%	85%	87%
79.3%	79%	84%	70%	87%	85%	66%	75%	82%	78%	81%	83%	84%	82%	80%	98%	77%	84%	58%	74%	73%	86%
64.3%	71%	67%	71%	76%	75%	64%	59%	64%	60%	71%	68%	46%	63%	47%	70%	72%	64%	53%	62%	53%	74%
88.4%	87%	89%	90%	87%	81%	92%	77%	92%	93%	90%	85%	95%	88%	96%	90%	85%	84%	88%	83%	95%	89%
77.0%	89%	79%	79%	89%	86%	44%	74%	88%	91%	90%	58%	64%	87%	56%	91%	88%	84%	80%	59%	59%	82%
68.8%	84%	81%	80%	76%	62%	36%	51%	71%	56%	81%	75%	70%	64%	68%	79%	79%	76%	80%	52%	62%	62%
85.0%	92%	86%	93%	93%	86%	86%	77%	72%	86%	86%	86%	86%	89%	86%	83%	84%	78%	75%	86%	86%	89%
77.5%	88%	90%	86%	83%	49%	81%	86%	80%	84%	77%	91%	82%	72%	68%	86%	83%	75%	66%	66%	81%	53%
81.9%	89%	83%	86%	90%	88%	75%	75%	89%	84%	77%	81%	91%	64%	91%	83%	74%	82%	77%	85%	63%	92%
78.9%	77%	88%	90%	81%	90%	80%	88%	78%	81%	82%	87%	88%	86%	78%	72%	77%	65%	64%	77%	64%	64%
81.4%	93%	86%	86%	86%	60%	74%	82%	85%	78%	85%	83%	72%	89%	73%	85%	88%	91%	83%	94%	73%	64%
83.2%	86%	75%	70%	67%	83%	93%	75%	73%	80%	78%	93%	71%	78%	93%	97%	93%	90%	87%	93%	87%	85%
79.2%	92%	93%	93%	89%	82%	66%	87%	87%	85%	91%	72%	70%	89%	69%	90%	92%	58%	49%	76%	79%	54%
59.1%	69%	76%	65%	65%	74%	48%	59%	50%	56%	71%	59%	46%	60%	46%	72%	75%	47%	35%	64%	52%	53%
67.6%	84%	72%	85%	90%	88%	32%	51%	73%	66%	84%	50%	62%	77%	49%	76%	76%	44%	81%	54%	76%	50%
71.7%	77%	63%	66%	67%	75%	58%	84%	73%	75%	84%	76%	65%	66%	76%	77%	82%	79%	58%	62%	76%	67%
87.8%	92%	94%	89%	92%	90%	82%	90%	89%	84%	91%	87%	82%	91%	84%	92%	88%	86%	86%	86%	82%	87%
80.0%	92%	88%	91%	87%	77%	52%	85%	90%	82%	94%	74%	77%	92%	65%	87%	91%	72%	93%	46%	62%	84%
82.0%	88%	89%	90%	93%	82%	66%	88%	85%	85%	83%	71%	89%	88%	73%	93%	92%	88%	78%	59%	75%	67%
79.3%	80%	80%	69%	73%	79%	90%	90%	88%	69%	80%	86%	65%	86%	87%	79%	73%	70%	65%	88%	87%	81%
76.7%	77%	81%	89%	77%	80%	80%	78%	73%	81%	81%	77%	84%	85%	84%	79%	73%	65%	66%	72%	65%	64%
76.9%	79%	77%	85%	76%	80%	65%	91%	77%	82%	79%	84%	62%	76%	65%	71%	81%	68%	90%	90%	70%	66%
69.5%	68%	79%	73%	68%	52%	63%	70%	72%	75%	74%	76%	62%	74%	74%	69%	72%	67%	78%	74%	61%	59%
70.9%	84%	83%	84%	87%	79%	36%	62%	73%	75%	86%	49%	69%	80%	49%	82%	81%	44%	69%	53%	80%	84%
81.6%	89%	91%	86%	89%	87%	63%	84%	87%	89%	91%	69%	69%	85%	63%	87%	86%	85%	82%	58%	78%	95%
71.0%	87%	85%	88%	86%	77%	63%	76%	62%	62%	62%	62%	59%	62%	62%	75%	69%	61%	69%	65%	79%	79%
69.1%	80%	70%	76%	84%	83%	54%	52%	76%	71%	78%	59%	30%	72%	50%	79%	74%	57%	81%	71%	77%	77%
72.2%	72%	73%	69%	66%	75%	80%	72%	66%	72%	60%	81%	83%	70%	84%	64%	75%	71%	80%	84%	68%	52%
77.0%	74%	77%	96%	71%	0%	80%	87%	84%	92%	71%	71%	83%	79%	76%	96%	84%	80%	79%	80%	90%	67%
63.0%	81%	70%	52%	76%	0%	67%	60%	63%	56%	76%	76%	64%	68%	70%	52%	63%	67%	72%	67%	62%	62%
85.0%	93%	83%	86%	88%	87%	82%	79%	84%	83%	86%	84%	82%	84%	83%	88%	86%	86%	84%	83%	85%	89%
67.4%	77%	89%	74%	87%	60%	58%	43%	47%	66%	68%	53%	78%	65%	64%	82%	64%	62%	54%	82%	78%	65%
77.9%	86%	86%	87%	87%	79%	70%	80%	82%	84%	85%	76%	58%	82%	60%	83%	80%	84%	74%	54%	76%	82%
80.4%	88%	72%	76%	72%	83%	92%	78%	60%	84%	69%	92%	94%	78%	95%	82%	78%	85%	78%	85%	74%	73%
79.8%	80%	81%	84%	86%	87%	77%	81%	84%	87%	92%	86%	78%	82%	78%	98%	95%	71%	67%	90%	41%	51%
82.0%	90%	91%	92%	95%	65%	70%	85%	90%	86%	85%	79%	92%	85%	66%	94%	84%	79%	76%	66%	79%	72%
87.8%	85%	99%	81%	93%	0%	98%	90%	93%	86%	93%	93%	94%	99%	99%	81%	93%	97%	99%	97%	99%	74%
74.0%	83%	77%	67%	78%	79%	66%	80%	80%	84%	85%	70%	53%	78%	68%	79%	80%	68%	28%	81%	82%	87%
69.6%	78%	72%	67%	69%	70%	52%	73%	74%	77%	75%	63%	75%	71%	71%	69%	71%	70%	73%	73%	67%	52%
66.2%	78%	75%	84%	75%	76%	61%	59%	44%	48%	71%	69%	60%	61%	61%	68%	74%	60%	73%	62%	53%	79%

Model Similarity Dendrogram

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