	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	2nd 74.4%	7th 71.9%	1st 74.9%	3rd 73.5%	15th 67.7%	20th 65.2%	5th 72.0%	11th 70.4%	10th 70.7%	4th 72.7%	12th 70.3%	18th 66.0%	9th 71.3%	16th 66.9%	8th 71.9%	6th 71.9%	13th 68.7%	21st 65.1%	14th 68.2%	19th 65.8%	17th 66.7%
85.6%	79%	88%	89%	88%	78%	67%	96%	96%	98%	80%	86%	87%	87%	86%	97%	91%	87%	85%	75%	86%	72%
59.9%	69%	63%	69%	66%	44%	65%	63%	68%	49%	57%	65%	70%	66%	70%	57%	48%	48%	44%	69%	58%	50%
76.9%	78%	72%	78%	85%	66%	79%	77%	81%	70%	81%	78%	86%	86%	79%	68%	78%	72%	66%	81%	86%	68%
77.6%	79%	92%	78%	78%	76%	84%	79%	75%	72%	80%	85%	76%	78%	67%	80%	80%	81%	58%	78%	76%	78%
65.1%	70%	61%	70%	70%	72%	71%	70%	62%	62%	57%	66%	68%	61%	63%	71%	63%	59%	63%	70%	62%	57%
65.7%	71%	71%	70%	71%	75%	69%	66%	70%	60%	65%	65%	58%	58%	56%	61%	69%	69%	61%	66%	52%	76%
78.0%	76%	78%	84%	76%	73%	84%	83%	82%	83%	83%	80%	73%	83%	70%	83%	82%	72%	71%	68%	73%	82%
66.1%	70%	69%	75%	69%	70%	49%	75%	70%	71%	76%	55%	60%	66%	63%	70%	70%	66%	59%	58%	59%	69%
82.3%	93%	90%	93%	97%	87%	62%	82%	84%	79%	84%	84%	93%	84%	82%	93%	90%	95%	50%	79%	77%	50%
73.1%	74%	74%	75%	73%	76%	76%	71%	57%	76%	72%	76%	76%	71%	76%	73%	71%	71%	72%	76%	76%	74%
70.9%	73%	74%	82%	77%	62%	78%	77%	76%	69%	66%	67%	63%	59%	61%	81%	69%	64%	47%	81%	81%	82%
75.1%	75%	77%	82%	74%	82%	74%	79%	82%	76%	87%	77%	63%	72%	80%	82%	80%	60%	61%	70%	79%	66%
57.9%	63%	65%	65%	64%	62%	49%	60%	57%	60%	60%	55%	56%	60%	55%	57%	59%	57%	47%	50%	57%	57%
63.6%	65%	66%	67%	61%	68%	61%	63%	64%	71%	65%	63%	54%	65%	54%	62%	71%	61%	58%	64%	64%	68%
77.7%	75%	72%	77%	66%	83%	86%	68%	59%	77%	79%	87%	69%	77%	85%	76%	80%	87%	86%	85%	66%	92%
60.8%	66%	66%	66%	60%	59%	50%	68%	62%	64%	58%	60%	52%	64%	54%	68%	59%	60%	59%	63%	63%	56%
58.6%	62%	65%	65%	65%	61%	50%	65%	35%	59%	56%	65%	50%	50%	51%	60%	72%	67%	63%	56%	42%	72%
55.1%	70%	63%	67%	77%	58%	32%	50%	63%	48%	59%	49%	53%	55%	37%	56%	54%	53%	64%	45%	66%	38%
69.1%	83%	65%	80%	73%	32%	51%	65%	84%	85%	87%	70%	47%	88%	53%	75%	73%	79%	74%	66%	55%	67%
75.0%	83%	74%	83%	71%	64%	67%	83%	79%	81%	86%	81%	65%	84%	72%	86%	87%	65%	60%	74%	65%	65%
64.9%	70%	71%	71%	68%	73%	48%	71%	65%	71%	72%	62%	62%	71%	65%	64%	68%	62%	54%	48%	57%	69%
71.5%	75%	80%	78%	69%	44%	64%	79%	75%	80%	78%	78%	73%	79%	77%	64%	79%	68%	73%	66%	54%	69%
67.3%	73%	66%	72%	69%	71%	69%	72%	67%	63%	68%	69%	46%	61%	74%	70%	63%	69%	68%	69%	67%	67%
74.1%	78%	74%	89%	78%	75%	68%	74%	71%	78%	75%	75%	69%	79%	82%	71%	70%	64%	71%	73%	71%	71%
64.0%	60%	64%	65%	67%	64%	66%	64%	64%	67%	63%	60%	60%	64%	65%	67%	64%	64%	55%	68%	73%	61%
63.0%	69%	55%	68%	69%	56%	48%	54%	64%	54%	69%	63%	61%	66%	63%	73%	78%	61%	73%	59%	66%	53%
70.5%	77%	74%	77%	79%	79%	50%	67%	77%	72%	82%	53%	71%	76%	62%	71%	78%	72%	72%	71%	68%	53%
69.0%	74%	76%	69%	78%	76%	41%	71%	74%	80%	75%	63%	60%	70%	60%	70%	71%	70%	59%	58%	70%	83%
74.6%	81%	90%	85%	85%	84%	70%	80%	73%	68%	70%	68%	70%	63%	67%	80%	70%	68%	65%	80%	67%	82%
53.7%	71%	63%	71%	71%	79%	32%	45%	60%	58%	59%	55%	51%	47%	32%	51%	58%	56%	49%	58%	31%	31%
74.8%	80%	79%	71%	71%	74%	73%	74%	71%	73%	74%	77%	73%	80%	77%	68%	72%	74%	77%	76%	77%	79%
84.2%	84%	90%	84%	78%	97%	84%	86%	81%	92%	81%	84%	76%	76%	84%	86%	85%	86%	93%	81%	71%	90%
67.0%	69%	64%	69%	76%	57%	70%	68%	72%	62%	72%	69%	77%	77%	70%	63%	67%	68%	61%	72%	44%	59%
69.3%	76%	71%	70%	76%	63%	64%	73%	72%	66%	69%	66%	65%	64%	66%	76%	74%	72%	71%	63%	65%	73%
74.6%	79%	68%	82%	74%	53%	79%	80%	81%	82%	81%	84%	71%	80%	67%	80%	80%	84%	85%	56%	60%	60%
70.3%	76%	75%	75%	79%	43%	69%	74%	72%	67%	86%	70%	60%	73%	65%	76%	70%	66%	67%	58%	77%	78%
65.0%	71%	67%	59%	52%	66%	81%	59%	49%	64%	58%	76%	58%	62%	81%	57%	66%	75%	86%	76%	54%	48%
77.8%	85%	65%	85%	78%	77%	93%	86%	87%	85%	85%	68%	62%	93%	63%	88%	84%	59%	72%	88%	56%	75%
72.4%	84%	77%	82%	82%	59%	57%	82%	81%	73%	83%	67%	73%	81%	55%	80%	78%	71%	55%	55%	72%	73%
91.5%	92%	86%	92%	99%	80%	93%	91%	95%	84%	95%	92%	100%	100%	93%	86%	92%	91%	84%	95%	100%	82%
69.2%	79%	67%	68%	70%	71%	65%	75%	76%	77%	70%	75%	59%	75%	70%	73%	71%	72%	30%	63%	73%	75%
67.5%	72%	68%	64%	72%	66%	65%	75%	65%	68%	79%	69%	65%	65%	67%	72%	65%	62%	62%	69%	64%	63%
52.1%	52%	57%	61%	61%	57%	51%	57%	29%	44%	45%	65%	58%	48%	56%	48%	44%	48%	70%	57%	51%	36%

Model Similarity Dendrogram

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