	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	2nd 78.1%	4th 76.8%	3rd 77.5%	1st 78.6%	9th 74.5%	18th 69.0%	12th 74.1%	15th 71.3%	13th 73.1%	11th 74.1%	8th 75.0%	17th 69.2%	10th 74.5%	7th 75.5%	5th 75.7%	6th 75.6%	21st 66.8%	19th 68.6%	14th 71.9%	16th 69.7%	20th 67.3%
85.0%	93%	91%	76%	90%	92%	68%	90%	81%	88%	87%	87%	86%	92%	86%	82%	89%	76%	77%	88%	89%	78%
79.5%	82%	80%	84%	84%	56%	81%	83%	79%	70%	90%	84%	81%	86%	78%	77%	77%	81%	71%	85%	81%	80%
69.6%	72%	70%	79%	79%	59%	75%	69%	82%	59%	82%	82%	82%	72%	74%	62%	75%	76%	63%	66%	66%	18%
72.1%	73%	69%	71%	71%	74%	66%	76%	77%	78%	73%	73%	71%	69%	75%	77%	78%	67%	69%	65%	69%	74%
83.0%	94%	80%	94%	97%	91%	86%	94%	81%	81%	78%	78%	75%	84%	84%	80%	79%	84%	56%	94%	68%	86%
91.2%	89%	95%	94%	91%	94%	95%	94%	86%	96%	91%	96%	86%	96%	95%	88%	89%	91%	96%	89%	83%	82%
70.8%	75%	77%	69%	74%	80%	62%	75%	75%	72%	70%	71%	79%	73%	86%	59%	78%	68%	68%	81%	46%	48%
76.2%	87%	78%	79%	81%	86%	52%	83%	83%	72%	72%	82%	71%	78%	71%	86%	86%	77%	62%	70%	60%	85%
77.2%	82%	78%	76%	76%	81%	64%	80%	76%	80%	80%	82%	88%	76%	75%	78%	73%	77%	81%	71%	89%	59%
77.9%	77%	92%	80%	84%	65%	86%	68%	76%	76%	75%	82%	74%	84%	90%	86%	82%	74%	61%	89%	68%	67%
70.8%	68%	75%	75%	75%	68%	68%	71%	75%	70%	73%	71%	69%	75%	75%	68%	74%	72%	63%	64%	70%	68%
77.1%	85%	77%	79%	79%	79%	79%	74%	81%	73%	78%	75%	78%	79%	76%	81%	76%	64%	74%	78%	75%	79%
69.7%	70%	72%	70%	86%	71%	70%	58%	60%	70%	80%	80%	44%	72%	67%	80%	71%	61%	57%	78%	75%	72%
61.7%	72%	68%	68%	73%	69%	49%	73%	64%	64%	56%	65%	41%	60%	67%	63%	59%	56%	67%	63%	63%	36%
60.4%	62%	66%	66%	66%	55%	54%	70%	71%	63%	60%	47%	61%	63%	60%	54%	61%	62%	51%	50%	67%	60%
66.7%	70%	69%	72%	77%	79%	53%	64%	69%	64%	62%	61%	68%	72%	66%	71%	69%	70%	70%	67%	48%	59%
80.1%	89%	90%	84%	77%	80%	80%	94%	61%	76%	76%	79%	64%	76%	76%	95%	92%	88%	71%	68%	80%	86%
55.1%	68%	59%	57%	71%	61%	39%	54%	43%	54%	48%	54%	61%	57%	57%	62%	62%	36%	59%	40%	58%	58%
67.3%	87%	56%	87%	81%	87%	45%	70%	70%	67%	66%	66%	62%	63%	64%	82%	89%	51%	50%	50%	65%	55%
73.0%	85%	76%	84%	78%	80%	72%	83%	61%	68%	76%	78%	61%	74%	78%	80%	74%	64%	71%	79%	43%	69%
70.8%	74%	69%	82%	76%	75%	74%	73%	59%	73%	85%	72%	65%	70%	76%	69%	68%	51%	68%	73%	70%	65%
80.0%	84%	79%	79%	83%	89%	82%	86%	68%	85%	82%	89%	72%	92%	93%	87%	70%	58%	73%	83%	83%	64%
78.3%	76%	80%	86%	79%	85%	83%	75%	77%	78%	73%	81%	77%	81%	82%	80%	79%	77%	81%	73%	74%	68%
64.6%	70%	75%	74%	80%	71%	76%	47%	54%	64%	80%	70%	43%	66%	62%	73%	72%	36%	34%	71%	65%	73%
62.4%	68%	68%	66%	68%	72%	61%	61%	58%	62%	54%	73%	54%	58%	64%	54%	63%	48%	51%	72%	75%	60%
56.7%	56%	64%	63%	66%	67%	58%	58%	49%	53%	66%	68%	44%	58%	64%	58%	60%	45%	49%	63%	54%	28%
64.9%	70%	68%	66%	71%	66%	49%	64%	57%	64%	65%	60%	66%	73%	68%	73%	71%	63%	68%	62%	70%	48%
67.5%	76%	69%	72%	72%	74%	40%	63%	71%	76%	59%	74%	72%	61%	53%	77%	74%	75%	75%	51%	63%	71%
77.1%	84%	79%	85%	85%	86%	75%	76%	77%	79%	76%	76%	70%	74%	72%	79%	81%	68%	74%	72%	75%	76%
72.8%	85%	84%	77%	92%	97%	60%	69%	77%	78%	64%	80%	56%	74%	72%	79%	75%	60%	72%	68%	55%	54%
75.6%	84%	80%	85%	85%	82%	72%	80%	69%	75%	76%	69%	71%	77%	77%	82%	77%	71%	61%	69%	68%	78%
67.7%	69%	75%	62%	62%	82%	66%	72%	59%	82%	59%	59%	59%	69%	67%	62%	66%	65%	73%	75%	69%	69%
72.1%	72%	66%	79%	79%	59%	75%	69%	82%	59%	82%	82%	82%	72%	74%	72%	69%	77%	67%	66%	66%	66%
82.5%	94%	91%	86%	83%	66%	63%	90%	88%	93%	83%	87%	79%	67%	89%	85%	90%	93%	92%	69%	49%	95%
76.9%	88%	81%	78%	78%	37%	94%	70%	81%	77%	81%	74%	69%	85%	93%	84%	77%	64%	95%	60%	89%	60%
60.8%	68%	67%	68%	62%	49%	67%	62%	68%	59%	67%	58%	56%	66%	60%	53%	60%	55%	58%	64%	54%	56%
79.0%	88%	81%	85%	89%	79%	74%	81%	68%	80%	86%	78%	77%	83%	84%	83%	79%	67%	63%	77%	79%	79%
87.5%	90%	95%	90%	86%	83%	91%	80%	94%	89%	95%	94%	75%	89%	91%	97%	97%	58%	84%	94%	79%	87%
70.9%	78%	76%	78%	82%	63%	66%	71%	73%	67%	81%	68%	69%	74%	72%	78%	78%	48%	50%	64%	82%	70%
91.2%	94%	96%	87%	87%	93%	91%	97%	83%	93%	83%	83%	83%	94%	91%	94%	80%	89%	99%	100%	99%	99%
79.3%	80%	84%	88%	82%	78%	67%	78%	78%	73%	84%	81%	78%	79%	83%	80%	79%	78%	79%	81%	73%	83%
62.1%	67%	65%	63%	63%	59%	57%	62%	60%	66%	66%	60%	71%	61%	63%	63%	67%	61%	55%	61%	56%	58%
81.3%	63%	92%	90%	81%	84%	80%	80%	64%	76%	68%	97%	85%	78%	96%	83%	87%	69%	93%	90%	86%	66%

Model Similarity Dendrogram

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