	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 72.7%	2nd 73.1%	4th 72.7%	13th 70.9%	21st 67.8%	20th 68.5%	14th 70.6%	1st 73.1%	8th 72.2%	12th 71.7%	3rd 72.7%	19th 68.6%	10th 72.0%	6th 72.6%	18th 68.8%	8th 72.2%	15th 70.5%	17th 69.1%	7th 72.3%	11th 71.9%	16th 69.7%
77.5%	85%	82%	82%	88%	74%	52%	71%	81%	76%	76%	82%	75%	76%	75%	87%	82%	82%	75%	69%	77%	80%
46.4%	40%	44%	44%	48%	22%	49%	36%	41%	31%	42%	53%	56%	47%	53%	42%	44%	61%	71%	62%		42%
74.3%	72%	76%	76%	76%	76%	82%	76%	71%	71%	82%	76%	76%	74%	76%	66%	78%	76%	70%	68%	66%	76%
59.8%	63%	66%	54%	55%	58%	65%	57%	65%	70%	58%	66%	56%	73%	79%	41%	45%	52%	55%	73%	54%	50%
74.3%	72%	80%	67%	67%	69%	84%	64%	66%	71%	73%	81%	80%	81%	83%	74%	72%	83%	74%	81%	74%	64%
79.7%	70%	73%	64%	68%	75%	93%	79%	78%	80%	77%	88%	83%	88%	86%	73%	77%	88%	66%	88%	97%	82%
85.3%	87%	86%	80%	77%	75%	89%	92%	87%	88%	92%	87%	86%	92%	84%	82%	86%	83%	79%	82%	89%	89%
68.6%	74%	68%	69%	78%	70%	46%	67%	68%	74%	74%	68%	75%	64%	64%	76%	75%	62%	77%	59%	72%	60%
82.0%	82%	86%	76%	82%	83%	68%	75%	83%	81%	83%	83%	78%	88%	83%	83%	86%	88%	90%	80%	93%	72%
55.6%	54%	57%	51%	66%	53%	58%	68%	65%	60%	51%	62%	48%	57%	66%	52%	55%	45%	48%	65%	50%	37%
55.5%	56%	59%	62%	63%	48%	57%	61%	62%	57%	55%	54%	46%	61%	46%	58%	64%	39%	36%	57%	59%	66%
59.8%	66%	66%	63%	64%	61%	53%	67%	69%	69%	59%	64%	40%	65%	65%	52%	60%	51%	52%	62%	52%	56%
60.9%	55%	63%	66%	55%	55%	69%	60%	68%	61%	57%	70%	58%	57%	60%	57%	52%	60%	58%	69%	60%	68%
81.7%	86%	83%	80%	87%	88%	80%	75%	85%	85%	80%	83%	76%	80%	76%	84%	89%	84%	81%	78%	75%	80%
82.0%	85%	90%	86%	79%	79%	82%	85%	77%	84%	89%	76%	77%	89%	85%	86%	84%	76%	80%	76%	86%	72%
77.2%	88%	77%	86%	77%	73%	63%	68%	78%	81%	79%	81%	79%	78%	79%	77%	81%	72%	77%	75%	73%	80%
57.3%	62%	65%	68%	68%	63%	51%	51%	54%	51%	56%	54%	51%	47%	51%	69%	66%	54%	39%	60%	55%	69%
62.0%	67%	64%	67%	67%	71%	44%	60%	69%	67%	64%	63%	61%	63%	61%	65%	65%	52%	53%	57%	59%	62%
60.8%	55%	53%	64%	52%	68%	27%	68%	67%	67%	74%	51%	49%	61%	44%	75%	79%	64%	73%	34%	80%	72%
76.4%	77%	78%	77%	75%	72%	80%	85%	70%	73%	80%	80%	86%	80%	77%	76%	77%	73%	57%	74%	81%	77%
86.0%	79%	83%	92%	79%	92%	77%	85%	84%	85%	91%	91%	78%	86%	91%	80%	85%	91%	89%	86%	91%	91%
71.0%	69%	70%	68%	56%	63%	81%	72%	76%	72%	71%	76%	57%	67%	73%	62%	73%	70%	65%	82%	87%	82%
83.9%	86%	84%	85%	87%	77%	79%	87%	89%	93%	90%	83%	61%	84%	86%	86%	85%	84%	85%	90%	92%	68%
76.2%	85%	82%	79%	79%	75%	69%	82%	86%	79%	73%	75%	69%	71%	73%	82%	80%	71%	70%	69%	71%	80%
78.5%	81%	89%	74%	75%	73%	72%	84%	78%	88%	75%	74%	82%	75%	83%	73%	73%	75%	75%	90%	84%	76%
75.3%	66%	77%	75%	68%	76%	79%	79%	61%	77%	77%	79%	80%	75%	81%	73%	69%	76%	71%	84%		82%
75.5%	89%	80%	82%	86%	80%	54%	67%	74%	75%	78%	62%	75%	81%	69%	77%	82%	74%	82%	72%	74%	72%
67.3%	77%	69%	76%	70%	53%	69%	69%	75%	64%	72%	64%	68%	60%	67%	66%	71%	71%	58%	58%	67%	69%
66.5%	62%	68%	66%	72%	60%	59%	78%	72%	62%	60%	75%	49%	66%	69%	74%	77%	67%	70%	75%	64%	52%
70.1%	77%	71%	72%	76%	74%	64%	65%	74%	73%	70%	64%	74%	73%	62%	79%	68%	60%	63%	70%	68%	75%
68.6%	72%	57%	71%	50%	54%	79%	62%	86%	77%	71%	73%	71%	68%	73%	47%	65%	79%	76%	82%	73%	54%
93.2%	97%	92%	92%	92%	92%	86%	92%	97%	97%	86%	92%	92%	94%	92%	92%	90%	92%	99%	99%	97%	96%
70.8%	70%	76%	76%	76%	76%	82%	76%	71%	71%	82%	76%	76%	74%	76%	0%	76%	74%	70%	68%	70%	70%
80.5%	80%	82%	80%	80%	73%	72%	81%	82%	87%	82%	81%	82%	87%	72%	75%	83%	86%	84%	79%	76%	86%
59.2%	63%	78%	77%	65%	32%	67%	39%	57%	59%	57%	61%	58%	71%	84%	51%	62%	56%	53%	71%	38%	44%
62.1%	62%	68%	64%	57%	48%	67%	68%	68%	57%	62%	63%	63%	60%	66%	62%	65%	63%	65%	53%	63%	61%
42.0%	42%	34%	39%	27%	47%	47%	33%	50%	47%	42%	46%	33%	38%	46%	35%	39%	53%	44%	46%	39%	54%
89.2%	83%	96%	98%	97%	93%	89%	91%	93%	96%	93%	93%	78%	96%	82%	94%	95%	80%	82%	83%	75%	87%
64.0%	67%	60%	72%	55%	57%	77%	68%	68%	68%	60%	69%	58%	54%	67%	63%	61%	60%	51%	63%	72%	74%
82.1%	84%	81%	81%	81%	81%	75%	81%	86%	86%	75%	81%	81%	83%	81%	79%	79%	81%	87%	89%	91%	81%
55.6%	64%	60%	63%	58%	52%	65%	46%	49%	42%	52%	61%	52%	52%	62%	57%	49%	59%	49%	64%	53%	58%
77.6%	81%	81%	75%	79%	79%	65%	85%	86%	68%	77%	78%	86%	81%	81%	86%	69%	81%	78%	81%	68%	64%
84.6%	92%	89%	85%	90%	77%	78%	82%	78%	83%	84%	85%	92%	78%	92%	89%	90%	84%	94%	84%	83%	68%

Model Similarity Dendrogram

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