	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	4th 73.7%	6th 73.2%	2nd 74.7%	1st 75.0%	7th 72.5%	21st 64.8%	3rd 74.2%	5th 73.6%	11th 70.1%	9th 71.3%	12th 70.0%	19th 65.9%	10th 70.5%	16th 67.8%	14th 69.4%	8th 71.3%	15th 69.2%	20th 65.2%	17th 66.8%	18th 66.8%	13th 69.5%
76.4%	79%	84%	80%	83%	81%	58%	83%	85%	79%	86%	73%	78%	73%	73%	83%	84%	66%	69%	63%	67%	78%
77.1%	91%	81%	86%	94%	76%	71%	75%	79%	62%	68%	71%	68%	77%	76%	87%	71%	79%	69%	81%	77%	80%
80.0%	80%	86%	87%	88%	85%	83%	78%	78%	72%	87%	80%	80%	80%	78%	77%	79%	76%	71%	74%		82%
56.8%	63%	61%	52%	60%	66%	52%	61%	49%	44%	59%	62%	39%	74%	63%	41%	51%	64%	70%	67%	42%	52%
87.0%	88%	88%	93%	93%	81%	87%	97%	92%	93%	83%	88%	88%	82%	83%	82%	84%	81%	67%	88%	94%	96%
77.9%	77%	84%	75%	79%	84%	54%	80%	80%	80%	81%	68%	80%	80%	67%	77%	84%	83%	94%	72%	83%	73%
74.6%	76%	79%	73%	83%	79%	67%	64%	74%	69%	85%	65%	73%	72%	54%	84%	86%	83%	83%	62%	74%	81%
59.7%	72%	71%	63%	71%	62%	37%	59%	58%	71%	79%	54%	63%	65%	54%	77%	71%	44%	48%	42%	47%	46%
81.1%	78%	82%	82%	81%	91%	78%	83%	81%	80%	75%	81%	81%	82%	81%	62%	84%	87%	95%	82%	87%	71%
57.2%	59%	65%	52%	66%	64%	52%	62%	53%	47%	61%	65%	33%	62%	56%	62%	51%	57%	45%	80%		51%
77.0%	76%	84%	87%	87%	57%	94%	82%	87%	77%	70%	82%	68%	82%	67%	66%	72%	58%	51%	86%	87%	97%
59.6%	66%	78%	55%	69%	73%	38%	62%	65%	46%	62%	70%	30%	63%	55%	69%	56%	61%	54%	64%	53%	63%
65.4%	56%	69%	74%	63%	81%	76%	67%	79%	72%	48%	74%	57%	71%	74%	52%	63%	80%	45%	72%	51%	50%
83.4%	88%	87%	89%	83%	88%	91%	86%	88%	91%	77%	90%	83%	86%	84%	71%	80%	80%	77%	84%	74%	75%
67.2%	75%	62%	81%	67%	70%	70%	80%	54%	77%	75%	72%	72%	70%	64%	65%	63%	70%	60%	53%	61%	50%
70.1%	71%	77%	81%	80%	77%	52%	83%	79%	75%	73%	66%	70%	72%	66%	69%	74%	67%	54%	56%	60%	70%
66.5%	75%	76%	77%	82%	74%	47%	62%	63%	68%	70%	56%	59%	58%	58%	72%	76%	53%	51%	63%	74%	83%
66.1%	76%	76%	70%	81%	71%	42%	63%	73%	62%	76%	62%	64%	62%	54%	73%	67%	49%	74%	59%	63%	71%
68.8%	74%	64%	70%	62%	66%	52%	88%	63%	64%	70%	67%	69%	75%	63%	87%	69%	63%	66%	64%	71%	77%
77.8%	82%	63%	79%	82%	80%	81%	74%	87%	82%	91%	74%	85%	76%	61%	81%	86%	82%	79%	60%	73%	75%
64.2%	56%	64%	77%	72%	71%	61%	75%	80%	73%	57%	68%	65%	66%	60%	49%	54%	61%	61%	49%	71%	58%
73.9%	79%	77%	90%	83%	81%	59%	86%	84%	81%	70%	80%	72%	75%	71%	62%	84%	69%	61%	57%	66%	65%
62.7%	72%	57%	68%	69%	71%	37%	71%	56%	53%	67%	66%	34%	50%	66%	72%	72%	72%	55%	68%	67%	74%
73.4%	73%	78%	70%	70%	72%	78%	84%	82%	74%	60%	79%	63%	71%	80%	67%	74%	77%	69%	77%	55%	89%
78.6%	80%	84%	85%	81%	81%	85%	84%	86%	84%	72%	79%	80%	80%	78%	66%	76%	78%	74%	78%	67%	72%
68.1%	72%	70%	73%	71%	72%	60%	69%	68%	69%	69%	65%	67%	68%	65%	70%	71%	66%	67%	62%	63%	74%
57.6%	73%	65%	63%	75%	58%	35%	53%	56%	54%	64%	43%	56%	57%	42%	64%	63%	55%	55%	46%	70%	63%
67.0%	78%	72%	76%	77%	62%	54%	78%	85%	71%	70%	67%	63%	67%	67%	66%	60%	64%	63%	49%	60%	57%
62.0%	66%	78%	63%	66%	77%	38%	65%	71%	47%	58%	61%	29%	58%	61%	72%	67%	66%	57%	64%	66%	73%
73.0%	85%	81%	79%	83%	88%	67%	64%	65%	73%	77%	76%	61%	65%	74%	83%	79%	74%	42%	66%	69%	83%
66.3%	70%	53%	77%	63%	62%	85%	88%	88%	82%	62%	58%	80%	71%	80%	46%	57%	71%	63%	60%	36%	41%
68.1%	67%	62%	61%	61%	63%	65%	70%	70%	76%	61%	68%	68%	68%	70%	67%	61%	72%	76%	73%	76%	75%
71.3%	68%	77%	77%	78%	75%	73%	69%	69%	63%	77%	70%	70%	70%	69%	72%	76%	66%	62%	65%	79%	72%
79.2%	83%	67%	89%	88%	90%	77%	70%	82%	82%	91%	67%	74%	73%	68%	90%	89%	85%	85%	56%	79%	79%
43.1%	55%	55%	39%	54%	32%	34%	40%	34%	33%	57%	45%	39%	63%	61%	34%	36%	39%	39%	63%	32%	21%
61.2%	59%	64%	70%	58%	50%	77%	68%	63%	59%	50%	63%	63%	55%	68%	52%	59%	66%	61%	68%	57%	56%
64.2%	53%	62%	68%	54%	61%	83%	80%	78%	54%	55%	70%	66%	70%	71%	47%	67%	60%	71%	69%	66%	44%
86.0%	91%	89%	93%	85%	81%	92%	94%	93%	92%	96%	93%	75%	75%	75%	84%	91%	74%	89%	77%	71%	96%
69.1%	83%	73%	78%	74%	73%	65%	74%	70%	74%	72%	68%	72%	70%	56%	66%	73%	72%	51%	60%	57%	70%
72.4%	72%	66%	65%	65%	68%	69%	74%	74%	80%	65%	72%	72%	72%	74%	72%	74%	77%	81%	78%	77%	74%
66.3%	73%	72%	78%	75%	61%	75%	75%	65%	62%	67%	70%	64%	64%	62%	76%	69%	66%	34%	60%	58%	67%
84.1%	88%	85%	86%	86%	83%	57%	84%	90%	86%	90%	83%	83%	83%	83%	91%	90%	83%	88%	82%	78%	88%
79.8%	71%	78%	82%	82%	81%	80%	88%	87%	82%	82%	79%	77%	77%	82%	81%	75%	79%	79%	75%	80%	78%

Model Similarity Dendrogram

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