	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	8th 75.8%	3rd 76.4%	12th 74.9%	4th 76.0%	2nd 76.4%	19th 71.8%	13th 74.6%	6th 75.9%	9th 75.6%	16th 74.1%	1st 76.5%	17th 73.8%	7th 75.8%	10th 75.4%	21st 65.0%	11th 75.1%	5th 75.9%	15th 74.2%	14th 74.2%	18th 73.0%	20th 71.4%
74.4%	70%	72%	66%	72%	82%	68%	79%	80%	77%	74%	82%	83%	77%	72%	67%	71%	67%	71%	70%	87%	75%
79.2%	79%	79%	83%	89%	67%	80%	76%	79%	60%	83%	84%	84%	82%	77%	81%	85%	85%	63%	81%	80%	86%
75.3%	73%	72%	75%	74%	87%	87%	81%	87%	81%	77%	77%	79%	74%	77%	68%	73%	68%	69%	69%	66%	68%
55.8%	54%	63%	54%	43%	60%	55%	69%	52%	54%	49%	61%	42%	66%	67%	43%	52%	55%	55%	73%	45%	59%
83.8%	79%	84%	84%	78%	74%	84%	79%	78%	78%	78%	95%	98%	85%	86%	82%	87%	87%	84%	92%	87%	81%
82.4%	87%	89%	87%	87%	89%	68%	80%	83%	86%	80%	75%	83%	80%	79%	80%	88%	84%	89%	77%	83%	77%
75.5%	69%	71%	72%	81%	80%	77%	69%	79%	83%	71%	77%	82%	74%	79%	59%	76%	89%	86%	69%	78%	65%
67.9%	67%	60%	64%	67%	77%	50%	67%	78%	76%	69%	75%	80%	67%	80%	56%	68%	71%	69%	66%	70%	49%
70.3%	71%	70%	66%	71%	75%	55%	66%	60%	67%	67%	67%	86%	69%	73%	71%	76%	86%	73%	70%	78%	60%
52.5%	54%	59%	42%	39%	58%	54%	62%	54%	51%	42%	62%	38%	56%	58%	43%	50%	60%	58%	75%	46%	41%
84.3%	89%	89%	90%	90%	82%	82%	88%	89%	87%	88%	89%	77%	87%	78%	83%	83%	72%	63%	90%	85%	89%
45.7%	51%	64%	38%	38%	57%	42%	40%	40%	47%	38%	57%	32%	45%	54%	0%	47%	63%	65%	56%	44%	41%
83.5%	86%	88%	78%	86%	84%	77%	92%	85%	89%	86%	85%	78%	90%	86%	79%	87%	82%	78%	78%	77%	82%
87.1%	80%	81%	85%	91%	83%	94%	83%	96%	94%	86%	96%	92%	90%	86%	72%	87%	96%	86%	86%	91%	74%
87.4%	96%	91%	96%	95%	87%	91%	83%	86%	82%	97%	82%	69%	91%	89%	88%	95%	86%	74%	89%	78%	90%
68.0%	65%	73%	68%	72%	69%	56%	61%	75%	69%	61%	76%	69%	71%	70%	62%	67%	68%	77%	61%	66%	71%
66.1%	74%	65%	66%	69%	79%	86%	62%	51%	67%	65%	61%	63%	61%	63%	80%	66%	65%	59%	64%	59%	63%
54.4%	53%	57%	53%	59%	56%	42%	52%	59%	59%	49%	58%	60%	55%	50%	51%	48%	59%	51%	58%	63%	50%
72.6%	76%	75%	79%	80%	54%	66%	81%	74%	64%	67%	70%	68%	80%	73%	63%	57%	76%	90%	81%	89%	62%
76.7%	68%	55%	64%	73%	82%	87%	75%	90%	90%	71%	76%	96%	74%	80%	68%	65%	92%	83%	78%	68%	75%
78.7%	82%	80%	79%	72%	77%	69%	85%	85%	88%	79%	85%	90%	83%	76%	77%	80%	63%	84%	71%	74%	73%
81.6%	88%	80%	86%	85%	91%	78%	85%	91%	94%	85%	87%	85%	87%	85%	0%	88%	89%	90%	71%	78%	91%
73.4%	91%	81%	84%	80%	86%	63%	74%	69%	77%	84%	73%	55%	66%	75%	0%	82%	72%	86%	80%	82%	82%
78.3%	78%	81%	79%	79%	79%	79%	85%	79%	88%	80%	70%	69%	84%	81%	78%	79%	76%	81%	69%	77%	74%
88.2%	88%	89%	88%	87%	85%	89%	92%	91%	90%	90%	95%	87%	94%	85%	82%	90%	93%	86%	91%	78%	82%
76.3%	80%	74%	75%	76%	77%	72%	71%	67%	74%	77%	80%	76%	76%	75%	79%	81%	80%	80%	78%	80%	75%
61.7%	65%	64%	64%	66%	66%	43%	62%	62%	68%	60%	56%	66%	61%	56%	61%	65%	66%	59%	56%	72%	58%
79.0%	79%	82%	80%	79%	83%	69%	83%	89%	92%	86%	81%	81%	82%	74%	84%	78%	73%	65%	66%	86%	66%
54.2%	48%	69%	57%	57%	45%	39%	50%	54%	48%	47%	58%	37%	54%	53%	54%	69%	55%	56%	69%	62%	57%
54.2%	44%	56%	47%	54%	64%	58%	48%	57%	56%	47%	66%	60%	50%	57%	36%	50%	61%	61%	55%	62%	50%
80.7%	89%	83%	89%	89%	88%	83%	77%	76%	76%	87%	74%	70%	82%	80%	86%	84%	79%	67%	83%	68%	85%
82.1%	84%	85%	82%	83%	70%	70%	76%	70%	76%	80%	80%	78%	83%	80%	95%	85%	88%	91%	88%	91%	89%
67.7%	66%	65%	67%	66%	79%	79%	73%	79%	73%	70%	70%	71%	67%	70%	61%	66%	63%	59%	61%	55%	62%
79.2%	84%	65%	80%	94%	85%	74%	71%	74%	79%	87%	78%	85%	81%	71%	79%	79%	85%	88%	70%	82%	73%
52.8%	54%	71%	54%	50%	45%	51%	44%	50%	47%	47%	50%	49%	62%	75%	43%	49%	48%	70%	67%	46%	36%
82.5%	88%	89%	94%	94%	83%	83%	87%	92%	75%	85%	83%	77%	85%	77%	80%	79%	77%	76%	74%	77%	78%
80.9%	87%	85%	96%	95%	93%	85%	86%	81%	84%	83%	80%	77%	86%	88%	0%	91%	80%	68%	88%	73%	92%
86.3%	83%	95%	90%	87%	82%	87%	89%	85%	83%	82%	88%	81%	89%	87%	92%	89%	92%	84%	91%	69%	87%
87.8%	95%	89%	94%	90%	88%	80%	94%	92%	86%	96%	83%	85%	87%	82%	92%	91%	88%	79%	75%	87%	91%
93.4%	95%	93%	96%	95%	92%	92%	98%	92%	98%	98%	98%	100%	95%	98%	91%	89%	91%	87%	89%	82%	93%
85.4%	88%	82%	94%	94%	90%	80%	91%	92%	86%	89%	88%	84%	80%	79%	93%	88%	79%	83%	71%	78%	85%
73.0%	71%	80%	67%	67%	76%	75%	76%	78%	72%	72%	80%	81%	76%	81%	58%	72%	76%	70%	71%	71%	63%
77.6%	91%	89%	69%	73%	79%	88%	66%	82%	81%	76%	83%	72%	77%	79%	77%	76%	80%	77%	73%	71%	71%

Model Similarity Dendrogram

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