	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 73.9%	1st 75.6%	7th 72.6%	3rd 74.1%	8th 72.2%	17th 69.9%	5th 73.3%	2nd 74.4%	15th 70.7%	12th 71.1%	13th 71.1%	20th 67.0%	9th 72.0%	14th 70.7%	11th 71.9%	6th 72.7%	16th 70.2%	21st 66.0%	18th 67.3%	19th 67.1%	10th 72.0%
70.0%	73%	73%	68%	68%	70%	65%	83%	82%	67%	75%	69%	72%	72%	70%	66%	70%	69%	54%	60%	73%	72%
71.6%	73%	67%	73%	74%	54%	58%	64%	66%	46%	82%	69%	77%	72%	69%	88%	86%	78%	72%	77%	68%	90%
52.6%	46%	61%	55%	53%	48%	61%	53%	56%	48%	56%	57%	59%	53%	53%	44%	52%	51%	51%	46%	44%	57%
60.8%	57%	63%	50%	49%	55%	66%	66%	52%	66%	57%	60%	62%	68%	79%		52%	64%	59%	62%	68%	62%
76.7%	74%	74%	81%	82%	77%	88%	91%	80%	82%	72%	76%	72%	71%	76%	78%	68%	75%	66%	74%	71%	83%
85.8%	93%	92%	92%	88%	95%	79%	89%	79%	87%	79%	79%	92%	93%	85%	66%	86%	92%	93%	78%	75%	90%
88.6%	95%	96%	89%	86%	84%	88%	90%	94%	90%	85%	92%	85%	90%	88%	91%	90%	87%	87%	87%	86%	80%
66.5%	76%	77%	69%	73%	73%	52%	75%	70%	71%	62%	62%	67%	70%	68%	59%	70%	62%	64%	54%	62%	60%
73.7%	75%	76%	60%	75%	76%	53%	65%	79%	67%	79%	76%	69%	78%	79%	75%	82%	80%	80%	65%	80%	78%
48.9%	45%	58%	40%	52%	49%	55%	71%	41%	55%	42%	53%	16%	48%	49%	51%	56%	55%	61%	49%	32%	49%
81.7%	94%	91%	87%	90%	92%	87%	78%	88%	90%	74%	90%	74%	78%	74%	90%	78%	64%	46%	76%	88%	87%
58.3%	59%	67%	46%	66%	66%	58%	58%	49%	48%	54%	61%	46%	55%	61%	57%	52%	70%	70%	65%	58%	59%
74.8%	77%	81%	84%	83%	77%	76%	67%	77%	69%	76%	80%	58%	72%	72%	80%	76%	74%	61%	72%	74%	84%
86.0%	92%	89%	82%	88%	91%	90%	81%	94%	93%	94%	83%	91%	94%	79%	77%	78%	78%	79%	80%	86%	86%
72.4%	81%	76%	74%	80%	78%	79%	72%	69%	71%	72%	68%	62%	72%	73%	75%	79%	76%	51%	73%	69%	71%
65.0%	70%	71%	67%	67%	68%	51%	66%	72%	70%	66%	64%	65%	63%	61%	63%	63%	63%	67%	57%	62%	68%
59.0%	64%	67%	67%	73%	61%	50%	51%	54%	65%	44%	61%	48%	50%	59%	60%	63%	62%	56%	62%	58%	65%
73.5%	72%	77%	75%	80%	73%	66%	85%	81%	70%	76%	71%	76%	76%	71%	76%	79%	60%	59%	73%	70%	78%
59.6%	65%	63%	64%	59%	55%	47%	61%	63%	62%	71%	47%	60%	68%	53%	72%	77%	49%	46%	47%	53%	69%
84.5%	87%	77%	92%	92%	82%	90%	88%	94%	83%	88%	82%	88%	89%	82%	79%	85%	65%	68%	81%	93%	89%
65.9%	69%	65%	73%	73%	67%	61%	71%	70%	71%	67%	62%	66%	63%	66%	71%	70%	57%	55%	59%	57%	70%
78.1%	76%	73%	89%	86%	88%	70%	92%	92%	92%	73%	81%	80%	78%	72%	77%	74%	67%	81%	63%	67%	69%
88.8%	91%	91%	89%	87%	93%	90%	91%	90%	86%	87%	92%	65%	87%	86%	89%	96%	94%	93%	91%	90%	86%
71.2%	78%	74%	79%	82%	74%	72%	67%	67%	68%	67%	72%	57%	68%	69%	77%	74%	72%	67%	65%	67%	80%
69.9%	70%	67%	69%	72%	76%	68%	73%	73%	73%	77%	56%	76%	70%	64%	67%	75%	72%	61%	64%	76%	69%
70.3%	72%	72%	78%	81%	66%	68%	70%	57%	67%	73%	74%	67%	69%	70%	76%	80%	66%	59%	68%		74%
63.4%	66%	66%	73%	72%	66%	53%	68%	65%	63%	65%	56%	62%	63%	60%	67%	67%	56%	58%	57%	63%	65%
61.1%	65%	69%	59%	65%	71%	49%	66%	75%	65%	61%	61%	58%	66%	58%	60%	67%	61%	43%	58%	48%	59%
58.4%	61%	73%	61%	63%	61%	47%	60%	61%	39%	44%	59%	38%	57%	57%	67%	66%	61%	71%	57%	61%	63%
75.4%	71%	82%	70%	69%	83%	71%	70%	75%	77%	81%	73%	71%	78%	69%	71%	72%	81%	80%	73%	81%	86%
57.9%	64%	65%	67%	66%	61%	67%	63%	69%	61%	61%	54%	54%	61%	58%	55%	53%	54%	36%	49%	47%	50%
83.0%	77%	92%	86%	84%	77%	93%	84%	87%	77%	87%	88%	90%	83%	83%	81%	82%	81%	81%	75%	73%	83%
95.0%	93%	92%	99%	99%	93%	91%	99%	97%	93%	97%	96%	94%	99%	99%	91%	98%	97%	97%	90%	88%	93%
83.0%	85%	87%	81%	68%	79%	89%	85%	85%	89%	87%	88%	88%	91%	90%	85%	85%	84%	54%	86%	73%	84%
72.0%	79%	94%	76%	78%	59%	83%	52%	84%	74%	68%	70%	32%	77%	86%	67%	71%	84%	87%	84%	52%	56%
64.5%	70%	73%	61%	60%	61%	72%	76%	72%	52%	63%	60%	64%	60%	65%	66%	58%	69%	64%	66%	59%	63%
55.1%	62%	61%	54%	60%	57%	62%	61%	61%	59%	57%	53%	53%	49%	54%	53%	54%	57%	45%	49%	46%	51%
76.6%	85%	76%	79%	81%	77%	78%	81%	90%	79%	86%	79%	67%	85%	66%	79%	77%	67%	71%	64%	65%	76%
64.9%	70%	69%	62%	68%	70%	63%	70%	81%	72%	61%	66%	65%	64%	62%	69%	68%	60%	54%	58%	46%	64%
92.0%	84%	98%	95%	93%	87%	97%	93%	97%	87%	97%	98%	100%	93%	93%	91%	92%	91%	91%	85%	83%	87%
66.1%	71%	71%	71%	72%	66%	70%	65%	67%	54%	70%	70%	67%	63%	64%	75%	67%	68%	47%	64%	64%	62%
71.3%	80%	78%	65%	65%	74%	65%	75%	79%	73%	60%	79%	57%	77%	77%	64%	67%	74%	78%	69%	77%	64%
69.1%	69%	68%	72%	66%	73%	69%	67%	66%	69%	66%	69%	73%	65%	73%	73%	71%	73%	74%	63%	66%	66%

Model Similarity Dendrogram

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