	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 76.5%	3rd 76.8%	1st 79.0%	2nd 77.6%	17th 71.1%	19th 70.0%	5th 76.7%	4th 76.7%	7th 75.9%	10th 74.8%	8th 75.4%	15th 72.5%	9th 75.0%	12th 73.1%	16th 71.7%	11th 73.1%	18th 70.5%	21st 66.9%	14th 72.6%	20th 68.4%	13th 72.6%
82.3%	85%	81%	90%	87%	74%	60%	86%	94%	84%	87%	86%	75%	82%	83%	85%	85%	76%	79%	71%	88%	90%
72.0%	73%	69%	82%	88%	45%	79%	70%	74%	63%	69%	70%	83%	62%	77%	71%	82%	62%	79%	70%	62%	83%
87.4%	93%	86%	93%	93%	92%	93%	80%	82%	76%	96%	93%	94%	84%	83%	93%	87%	86%	84%	83%	79%	86%
87.1%	90%	86%	86%	87%	85%	85%	90%	89%	83%	87%	90%	89%	87%	89%	89%	86%	85%	82%	83%	90%	91%
86.1%	91%	88%	88%	99%	81%	89%	96%	93%	96%	86%	82%	86%	86%	81%	72%	76%	88%	69%	90%	86%	85%
78.8%	77%	81%	77%	83%	79%	72%	81%	91%	88%	77%	84%	74%	79%	74%	78%	74%	84%	76%	75%	68%	83%
77.3%	76%	77%	83%	86%	85%	75%	77%	77%	82%	83%	72%	75%	67%	68%	79%	77%	81%	87%	64%	75%	77%
68.0%	75%	75%	69%	83%	77%	51%	69%	81%	69%	84%	68%	73%	71%	63%	69%	77%	70%	65%	53%	10%	76%
75.5%	68%	67%	81%	66%	82%	80%	86%	81%	83%	68%	79%	92%	78%	79%	64%	70%	70%	70%	82%	74%	66%
86.6%	90%	87%	91%	88%	85%	89%	85%	83%	89%	87%	90%	88%	87%	89%	87%	89%	82%	81%	86%	81%	84%
64.9%	74%	72%	75%	66%	51%	59%	67%	64%	58%	56%	64%	52%	57%	50%	62%	62%	58%	47%	89%	94%	85%
84.1%	83%	86%	85%	86%	86%	84%	86%	81%	85%	81%	83%	84%	86%	85%	83%	86%	83%	82%	84%	87%	80%
66.8%	54%	82%	71%	63%	79%	72%	71%	76%	79%	50%	82%	57%	73%	70%	46%	62%	74%	65%	74%	42%	60%
76.6%	82%	84%	83%	69%	73%	67%	84%	74%	72%	70%	80%	85%	85%	90%	77%	67%	72%	70%	88%	67%	69%
71.9%	67%	78%	84%	75%	75%	63%	83%	88%	75%	82%	67%	78%	81%	67%	56%	59%	59%	75%	61%	76%	61%
73.4%	77%	77%	80%	70%	70%	64%	84%	84%	73%	77%	80%	69%	72%	75%	69%	68%	71%	64%	73%	64%	81%
74.7%	83%	89%	89%	82%	61%	49%	73%	64%	78%	80%	78%	53%	76%	74%	82%	83%	62%	62%	81%	88%	81%
69.4%	82%	73%	81%	81%	73%	45%	64%	77%	70%	78%	65%	62%	74%	59%	81%	75%	66%	36%	65%	75%	76%
50.0%	52%	45%	54%	50%	60%	37%	59%	53%	50%	53%	50%	39%	48%	50%	59%	69%	46%	44%	38%	40%	53%
82.4%	81%	74%	80%	89%	83%	82%	78%	94%	89%	94%	82%	82%	85%	77%	89%	90%	80%	84%	70%	61%	86%
61.5%	65%	68%	73%	65%	52%	62%	80%	65%	67%	59%	72%	68%	68%	69%	50%	50%	48%	39%	57%	53%	61%
76.1%	80%	83%	89%	74%	83%	62%	85%	87%	81%	67%	82%	76%	80%	75%	76%	76%	59%	74%	59%	83%	68%
84.2%	94%	89%	86%	90%	72%	75%	86%	79%	87%	89%	74%	89%	85%	70%	88%	89%	83%	85%	82%	88%	88%
69.1%	56%	81%	70%	70%	74%	89%	71%	74%	76%	63%	89%	53%	74%	79%	64%	58%	79%	39%	79%	53%	60%
74.6%	73%	81%	83%	67%	77%	81%	81%	72%	73%	70%	84%	80%	78%	83%	67%	70%	63%	67%	84%	69%	63%
67.6%	71%	73%	73%	63%	64%	60%	68%	69%	70%	67%	69%	72%	70%	70%	66%	65%	66%	68%	70%	65%	61%
66.8%	81%	70%	77%	81%	79%	30%	56%	69%	61%	76%	48%	56%	71%	49%	78%	74%	69%	79%	52%	73%	74%
68.8%	79%	75%	79%	80%	61%	56%	79%	80%	71%	76%	76%	77%	70%	62%	59%	63%	63%	45%	66%	57%	70%
87.0%	92%	89%	91%	93%	92%	86%	91%	83%	82%	86%	85%	89%	83%	80%	90%	91%	89%	78%	86%	89%	82%
76.9%	85%	82%	88%	92%	72%	80%	74%	78%	80%	83%	76%	61%	80%	73%	84%	81%	81%	36%	77%	73%	79%
68.0%	71%	68%	85%	68%	55%	75%	80%	89%	77%	65%	74%	77%	78%	78%	51%	63%	58%	49%	71%	54%	42%
60.8%	49%	62%	56%	56%	56%	56%	67%	66%	72%	53%	56%	54%	64%	65%	62%	65%	65%	64%	65%	62%	61%
77.1%	77%	77%	83%	83%	83%	83%	71%	73%	66%	86%	83%	84%	75%	73%	79%	75%	73%	75%	73%	70%	77%
81.2%	80%	83%	77%	87%	90%	78%	83%	78%	87%	91%	86%	67%	73%	66%	89%	94%	84%	85%	62%	86%	79%
61.7%	88%	75%	55%	78%	54%	73%	40%	49%	73%	78%	42%	54%	67%	69%	48%	47%	39%	75%	80%	76%	35%
60.6%	57%	63%	61%	58%	39%	71%	60%	62%	66%	53%	73%	67%	66%	71%	47%	53%	71%	51%	68%	57%	58%
60.9%	59%	55%	75%	56%	26%	83%	75%	66%	76%	50%	77%	70%	72%	76%	45%	48%	65%	49%	80%	40%	36%
81.3%	83%	89%	91%	86%	93%	88%	95%	92%	90%	81%	88%	74%	76%	76%	83%	79%	61%	55%	81%	51%	96%
69.1%	81%	76%	80%	80%	58%	63%	76%	74%	74%	73%	72%	75%	72%	66%	58%	71%	52%	62%	54%	62%	73%
64.6%	53%	66%	60%	60%	60%	60%	72%	70%	77%	57%	60%	59%	68%	69%	60%	69%	69%	68%	69%	64%	66%
67.0%	77%	69%	75%	79%	58%	72%	73%	61%	57%	68%	65%	72%	66%	62%	73%	69%	64%	62%	62%	56%	67%
87.4%	99%	93%	92%	94%	90%	57%	82%	86%	78%	94%	90%	74%	90%	95%	91%	89%	92%	88%	87%	85%	90%
80.4%	87%	78%	74%	85%	75%	77%	85%	77%	82%	88%	78%	80%	77%	83%	84%	81%	83%	83%	78%	70%	84%

Model Similarity Dendrogram

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