	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
Score	3rd 71.0%	4th 70.7%	1st 72.0%	2nd 71.7%	16th 66.7%	15th 67.1%	10th 68.7%	6th 70.3%	9th 69.2%	7th 70.0%	13th 68.2%	17th 66.4%	12th 68.4%	14th 67.7%	8th 69.5%	5th 70.4%	18th 66.2%	20th 65.5%	19th 65.6%	11th 68.5%	21st 63.1%
65.9%	69%	69%	68%	73%	67%	67%	64%	69%	68%	68%	65%	58%	68%	65%	67%	67%	63%	54%	61%	73%	60%
72.3%	81%	69%	84%	76%	53%	77%	73%	77%	63%	84%	70%	75%	77%	70%	76%	71%	68%	75%	68%	72%	60%
91.4%	90%	90%	95%	93%	90%	97%	90%	97%	83%	97%	100%	90%	90%	91%	90%	93%	76%	97%	90%	97%	83%
78.7%	78%	90%	77%	90%	25%	90%	78%	70%	62%	76%	90%	91%	91%	79%	78%	69%	77%	84%	90%	92%	76%
85.0%	81%	83%	81%	80%	89%	76%	81%	86%	94%	86%	86%	89%	86%	89%	86%	81%	90%	86%	81%	86%	89%
81.6%	85%	90%	90%	90%	90%	85%	78%	85%	78%	85%	85%	78%	78%	71%	90%	90%	78%	92%	82%	64%	50%
55.0%	60%	54%	47%	54%	58%	49%	47%	56%	55%	54%	54%	66%	54%	66%	54%	57%	69%	58%	49%	44%	51%
58.5%	67%	67%	61%	67%	67%	39%	65%	60%	55%	67%	57%	51%	53%	53%	67%	67%	61%	44%	48%	58%	55%
71.9%	58%	73%	69%	61%	71%	61%	71%	86%	79%	75%	69%	71%	71%	70%	69%	68%	69%	76%	71%	86%	86%
83.0%	76%	91%	76%	76%	91%	91%	72%	76%	76%	76%	91%	91%	91%	91%	86%	83%	63%	77%	91%	91%	86%
70.6%	79%	73%	79%	77%	59%	79%	78%	78%	74%	55%	74%	83%	61%	58%	59%	77%	51%	53%	88%	96%	52%
71.4%	77%	85%	69%	85%	85%	70%	69%	69%	69%	64%	77%	79%	50%	79%	72%	64%	40%	64%	79%	75%	79%
66.4%	66%	74%	76%	74%	64%	78%	59%	60%	74%	59%	84%	70%	56%	74%	65%	62%	60%	56%	72%	56%	56%
68.1%	70%	70%	70%	70%	70%	79%	61%	60%	66%	70%	70%	72%	60%	67%	70%	67%	64%	64%	66%	72%	72%
77.8%	84%	86%	90%	90%	69%	64%	84%	90%	84%	70%	77%	84%	76%	68%	77%	86%	88%	75%	53%	88%	51%
65.7%	66%	60%	68%	57%	57%	68%	70%	60%	66%	66%	68%	50%	66%	67%	70%	66%	66%	63%	62%	95%	68%
78.4%	79%	75%	75%	90%	90%	78%	79%	78%	79%	79%	79%	73%	78%	78%	79%	75%	68%	74%	76%	78%	87%
36.5%	48%	43%	43%	48%	45%	21%	29%	43%	36%	37%	26%	26%	43%	32%	38%	38%	27%	50%	28%	36%	29%
51.7%	48%	40%	48%	40%	56%	27%	48%	58%	58%	63%	42%	48%	58%	40%	79%	72%	71%	42%	26%		70%
81.9%	80%	85%	85%	80%	75%	75%	85%	84%	90%	90%	79%	75%	90%	75%	80%	90%	82%	79%	90%	75%	76%
63.4%	69%	69%	69%	69%	72%	54%	66%	62%	66%	69%	59%	64%	66%	62%	68%	68%	72%	41%	47%	48%	72%
80.5%	87%	74%	74%	81%	89%	67%	83%	90%	83%	89%	61%	83%	89%	72%	83%	85%	77%	78%	70%	84%	91%
50.3%	55%	44%	50%	50%	73%	75%	56%	54%	50%	55%	49%	22%	41%	84%	44%	44%	44%	44%	50%	28%	44%
48.1%	54%	47%	53%	53%	46%	53%	44%	47%	54%	44%	54%	48%	44%	54%	46%	46%	44%	51%	47%	41%	41%
63.0%	68%	68%	68%	68%	64%	57%	61%	66%	68%	64%	59%	56%	60%	68%	59%	65%	64%	66%	64%	53%	57%
70.4%	69%	85%	69%	62%	54%	80%	72%	63%	72%	69%	78%	72%	69%	82%	65%	63%	72%	69%	72%	75%	67%
61.6%	64%	64%	64%	64%	58%	51%	54%	64%	64%	67%	57%	50%	64%	59%	68%	62%	64%	58%	67%	67%	63%
53.8%	56%	53%	53%	57%	66%	51%	53%	60%	60%	65%	52%	43%	52%	48%	53%	63%	53%	61%	32%	49%	49%
46.7%	51%	62%	64%	64%	57%	46%	57%	44%	44%	30%	38%	52%	37%	37%	57%	57%	30%	22%	52%	38%	42%
56.4%	70%	50%	70%	70%	47%	56%	65%	59%	62%	60%	55%	62%	55%	52%	58%	44%	32%	67%	55%	52%	44%
80.6%	90%	89%	100%	84%	87%	59%	84%	100%	88%	90%	82%	71%	87%	66%	53%	75%	100%	78%	66%	91%	52%
75.2%	74%	76%	61%	72%	76%	68%	76%	68%	83%	68%	66%	76%	76%	74%	76%	72%	90%	74%	76%	95%	83%
50.7%	50%	50%	63%	53%	50%	56%	50%	56%	44%	56%	59%	50%	50%	51%	50%	53%	38%	51%	50%	41%	44%
78.6%	83%	76%	83%	83%	52%	80%	81%	83%	78%	83%	75%	75%	83%	75%	83%	83%	82%	80%	75%	75%	83%
70.8%	72%	68%	67%	76%	44%	77%	67%	75%	72%	67%	63%	79%	75%	67%	78%	91%	83%	68%	68%	67%	62%
75.1%	79%	79%	83%	83%	52%	72%	78%	76%	76%	77%	76%	73%	76%	73%	83%	77%	76%	74%	66%	72%	77%
57.6%	61%	61%	66%	66%	56%	62%	56%	56%	61%	60%	62%	50%	59%	58%	49%	61%	60%	58%	50%	64%	34%
84.8%	73%	87%	88%	84%	81%	84%	97%	88%	93%	88%	88%	77%	88%	88%	88%	88%	77%	75%	85%	82%	82%
71.9%	76%	76%	68%	68%	75%	59%	76%	77%	69%	84%	61%	58%	84%	65%	84%	84%	77%	80%	58%	70%	60%
89.7%	91%	90%	95%	93%	90%	97%	90%	97%	83%	97%	100%	90%	90%	91%	90%	93%	76%	97%	90%	61%	83%
62.6%	72%	60%	76%	72%	69%	63%	67%	66%	58%	67%	65%	51%	63%	63%	61%	67%	67%	56%	60%	57%	35%
82.6%	91%	84%	85%	77%	91%	85%	83%	85%	91%	100%	71%	78%	85%	78%	85%	82%	83%	58%	91%	85%	67%
54.5%	55%	61%	74%	63%	47%	61%	55%	45%	47%	40%	61%	57%	53%	62%	55%	60%	53%	47%	57%	47%	45%

Model Similarity Dendrogram

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