	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 69.7%	10th 67.9%	3rd 70.4%	21st 62.7%	14th 66.7%	5th 68.8%	9th 68.1%	16th 66.5%	12th 67.1%	6th 68.3%	8th 68.2%	17th 65.2%	7th 68.2%	15th 66.7%	1st 70.6%	2nd 70.4%	19th 64.6%	20th 64.0%	13th 67.1%	18th 64.8%	11th 67.3%
71.1%	68%	68%	73%	68%	68%	85%	73%	60%	68%	73%	68%	67%	68%	78%	76%	67%	65%	73%	88%	73%	67%
83.7%	82%	85%	87%	75%	43%	90%	74%	87%	77%	87%	89%	89%	100%	89%	94%	89%	85%	79%	89%	84%	83%
71.2%	79%	71%	83%	0%	71%	75%	76%	75%	71%	75%	83%	83%	71%	71%	75%	75%	70%	71%	75%	75%	71%
70.6%	78%	53%	68%	59%	62%	64%	78%	70%	67%	78%	78%	78%	67%	78%	75%	75%	68%	71%	59%	78%	78%
84.9%	76%	84%	76%	76%	76%	76%	76%	91%	82%	91%	89%	89%	91%	84%	80%	100%	89%	91%	84%	91%	91%
72.3%	65%	60%	60%	60%	60%	80%	75%	65%	75%	75%	69%	80%	75%	75%	65%	65%	90%	84%	75%	90%	75%
60.8%	57%	57%	59%	59%	52%	55%	59%	65%	64%	57%	59%	72%	57%	59%	66%	74%	71%	69%	55%	50%	60%
67.4%	75%	63%	60%	68%	78%	50%	67%	67%	71%	74%	67%	67%	67%	56%	72%	70%	71%	75%	56%	67%	74%
72.1%	74%	66%	66%	66%	75%	60%	66%	75%	74%	74%	70%	80%	80%	70%	74%	79%	74%	52%	70%	90%	80%
78.8%	78%	77%	87%	85%	78%	78%	87%	83%	78%	74%	78%	74%	78%	78%	82%	87%	75%	69%	78%	78%	73%
54.2%	58%	57%	64%	64%	43%	62%	62%	68%	57%	50%	59%	64%	41%	50%	46%	50%	15%	32%	67%	62%	67%
72.1%	89%	74%	75%	75%	79%	69%	69%	69%	69%	67%	69%	69%	67%	69%	71%	77%	67%	72%	74%	74%	71%
44.3%	45%	45%	50%	47%	50%	61%	45%	39%	45%	42%	45%	50%	45%	50%	39%	39%	34%	34%	57%	34%	34%
65.5%	68%	62%	68%	62%	60%	65%	62%	61%	68%	68%	68%	50%	77%	77%	68%	72%	53%	67%	61%	77%	62%
80.4%	77%	77%	77%	77%	80%	91%	89%	80%	89%	75%	77%	73%	89%	87%	78%	78%	87%	86%	62%	89%	70%
80.0%	90%	80%	80%	68%	80%	74%	90%	81%	81%	83%	81%	65%	83%	74%	83%	86%	81%	85%	75%	90%	70%
69.1%	62%	82%	82%	73%	82%	68%	64%	59%	71%	64%	73%	75%	54%	65%	62%	82%	56%	63%	69%	70%	75%
62.3%	68%	68%	68%	68%	68%	45%	50%	69%	68%	62%	58%	44%	58%	52%	68%	68%	69%	68%	52%	68%	70%
36.8%	34%	34%	34%	34%	100%	26%	34%	41%	34%	41%	28%	12%	34%	28%	61%	47%	28%	22%	20%	47%	34%
60.5%	69%	67%	67%	67%	56%	63%	58%	56%	56%	60%	57%	56%	65%	58%	64%	67%	56%	55%	61%	56%	56%
51.3%	46%	52%	60%	60%	45%	67%	52%	37%	52%	52%	52%	64%	52%	64%	50%	52%	45%	34%	60%	44%	38%
63.9%	65%	68%	65%	73%	48%	75%	65%	48%	57%	66%	67%	67%	68%	68%	66%	60%	61%	49%	75%	66%	65%
50.2%	46%	47%	56%	47%	51%	58%	47%	56%	49%	54%	47%	49%	57%	58%	52%	47%	47%	43%	47%	54%	43%
70.9%	70%	70%	70%	71%	88%	86%	74%	80%	73%	67%	73%	58%	70%	88%	73%	59%	51%	66%	82%	51%	68%
74.0%	73%	73%	73%	82%	87%	69%	87%	66%	73%	73%	82%	59%	66%	73%	82%	72%	65%	82%	73%	87%	58%
65.2%	67%	75%	65%	67%	65%	75%	74%	55%	56%	67%	67%	70%	67%	68%	63%	62%	60%	59%	63%	65%	60%
83.3%	82%	82%	90%	90%	89%	75%	82%	80%	82%	87%	76%	82%	87%	85%	82%	87%	89%	82%	76%	75%	89%
78.3%	88%	88%	88%	76%	66%	63%	85%	71%	74%	88%	80%	66%	88%	70%	87%	82%	80%	75%	70%	71%	88%
74.9%	82%	91%	100%	100%	73%	62%	91%	64%	73%	62%	74%	62%	57%	43%	74%	88%	57%	75%	88%		82%
66.4%	75%	67%	75%	75%	65%	74%	64%	60%	60%	67%	67%	50%	67%	62%	68%	71%	63%	49%	59%	74%	82%
67.5%	70%	63%	70%	70%	63%	72%	63%	49%	63%	66%	80%	75%	65%	73%	77%	61%	57%	51%	88%	63%	79%
76.9%	80%	88%	84%	0%	88%	85%	85%	85%	88%	85%	77%	77%	88%	88%	85%	81%	92%	88%	85%	0%	85%
44.6%	51%	44%	48%	0%	44%	47%	44%	47%	44%	47%	54%	54%	44%	44%	44%	50%	41%	44%	47%	54%	44%
68.5%	79%	74%	74%	81%	57%	56%	59%	83%	74%	79%	67%	56%	74%	57%	74%	74%	76%	75%	56%	56%	57%
61.3%	71%	57%	71%	65%	47%	72%	54%	79%	54%	57%	47%	47%	71%	47%	71%	71%	68%	71%	47%	74%	47%
43.7%	47%	47%	48%	47%	29%	48%	45%	47%	41%	43%	41%	45%	47%	40%	47%	43%	38%	43%	47%	47%	38%
67.4%	54%	60%	63%	63%	59%	79%	62%	55%	70%	70%	70%	70%	70%	82%	67%	70%	52%	80%	80%	76%	63%
65.0%	76%	66%	68%	68%	76%	75%	68%	68%	60%	68%	66%	55%	68%	61%	68%	69%	53%	51%	61%	53%	68%
69.1%	68%	68%	71%	90%	56%	83%	68%	68%	62%	74%	71%	79%	73%	66%	68%	73%	58%	50%	68%	62%	75%
83.6%	88%	96%	85%	0%	96%	92%	92%	92%	96%	92%	85%	85%	96%	96%	96%	89%	100%	96%	92%	0%	92%
66.4%	74%	69%	75%	74%	65%	70%	74%	76%	64%	69%	75%	52%	57%	50%	84%	74%	70%	18%	50%	70%	84%
88.2%	90%	90%	90%	90%	90%	81%	84%	84%	90%	83%	91%	90%	90%	80%	92%	93%	91%	91%	90%	91%	82%
55.8%	61%	55%	55%	57%	60%	59%	57%	50%	66%	50%	58%	55%	45%	55%	66%	53%	61%	64%	55%	45%	45%

Model Similarity Dendrogram

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