	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 69.8%	8th 68.7%	3rd 69.6%	6th 69.2%	11th 67.9%	18th 65.0%	7th 68.8%	13th 67.1%	9th 68.6%	5th 69.3%	10th 68.3%	20th 64.1%	14th 66.8%	16th 65.2%	1st 70.2%	4th 69.3%	17th 65.1%	21st 62.6%	19th 64.4%	12th 67.3%	15th 65.7%
80.6%	82%	77%	88%	85%	77%	77%	74%	72%	90%	100%	90%	77%	75%	76%	74%	81%	77%	74%	80%	88%	78%
63.9%	70%	51%	64%	74%	27%	73%	69%	64%	60%	64%	70%	70%	64%	64%	69%	62%	53%	57%	62%	67%	88%
49.6%	51%	50%	51%	55%	44%	53%	47%	54%	44%	47%	54%	69%	47%	54%	41%	41%	59%	51%	47%	41%	41%
65.6%	71%	60%	62%	71%	77%	53%	71%	62%	62%	71%	61%	70%	67%	55%	71%	71%	61%	67%	60%	70%	65%
73.2%	76%	70%	81%	76%	80%	70%	76%	70%	72%	78%	63%	70%	70%	75%	70%	67%	72%	72%	70%	80%	79%
83.5%	91%	82%	82%	82%	71%	82%	81%	68%	87%	91%	81%	87%	81%	80%	91%	91%	82%	94%	87%	87%	76%
75.7%	80%	77%	82%	82%	80%	71%	82%	80%	80%	82%	68%	80%	82%	82%	65%	63%	79%	80%	68%	74%	53%
73.9%	78%	78%	59%	63%	82%	63%	79%	70%	70%	82%	78%	78%	82%	65%	80%	82%	81%	71%	67%	84%	60%
85.0%	89%	88%	82%	82%	91%	78%	80%	89%	91%	82%	89%	80%	82%	79%	84%	91%	87%	86%	89%	83%	83%
71.4%	84%	82%	67%	76%	58%	65%	66%	75%	69%	76%	74%	70%	84%	69%	59%	76%	60%	64%	80%	78%	68%
49.3%	54%	54%	54%	54%	54%	69%	54%	62%	48%	47%	45%	52%	31%	45%	54%	46%	22%	13%	62%	54%	62%
77.8%	75%	75%	83%	78%	73%	78%	71%	78%	89%	74%	74%	70%	74%	89%	78%	78%	88%	85%	78%	76%	70%
77.9%	87%	81%	87%	76%	78%	87%	65%	70%	75%	88%	100%	55%	73%	78%	78%	83%	76%	68%	75%	74%	81%
74.4%	78%	74%	74%	74%	72%	66%	86%	72%	89%	78%	74%	74%	77%	74%	85%	89%	73%	73%	76%	52%	52%
79.0%	87%	83%	89%	87%	71%	77%	79%	76%	78%	84%	77%	74%	71%	89%	84%	77%	73%	73%	81%	75%	73%
70.8%	66%	68%	75%	73%	66%	67%	67%	67%	68%	68%	77%	43%	66%	71%	73%	73%	72%	62%	64%	100%	100%
60.9%	69%	75%	76%	67%	73%	64%	63%	50%	58%	50%	69%	76%	48%	58%	67%	72%	43%	41%	65%	42%	52%
52.9%	60%	47%	61%	61%	61%	32%	52%	72%	56%	51%	54%	33%	61%	55%	56%	49%	46%	50%	38%	60%	56%
35.1%	37%	22%	45%	37%	78%	22%	31%	32%	29%	52%	37%	22%	39%	22%	69%	54%	37%	22%	9%	31%	10%
60.0%	64%	63%	64%	64%	60%	63%	60%	47%	60%	64%	55%	60%	60%	60%	64%	55%	55%	54%	58%	69%	60%
62.9%	58%	65%	58%	57%	62%	69%	61%	55%	64%	66%	73%	55%	62%	66%	64%	67%	54%	61%	70%	64%	70%
73.1%	68%	78%	73%	73%	76%	80%	65%	62%	66%	78%	87%	57%	73%	73%	78%	87%	77%	73%	85%	73%	54%
57.8%	64%	62%	56%	59%	60%	56%	53%	62%	56%	62%	58%	55%	54%	65%	64%	53%	54%	55%	53%		55%
66.7%	68%	71%	75%	75%	61%	77%	59%	59%	68%	74%	66%	48%	66%	61%	72%	61%	66%	62%	61%	61%	89%
81.4%	87%	75%	73%	80%	87%	81%	87%	85%	87%	87%	69%	87%	87%	70%	78%	88%	89%	89%	89%	74%	60%
64.1%	58%	66%	71%	60%	66%	76%	67%	55%	58%	63%	68%	74%	58%	66%	60%	58%	74%	62%	66%	58%	63%
60.8%	61%	57%	68%	61%	59%	46%	60%	73%	65%	59%	54%	65%	59%	59%	65%	53%	52%	57%	52%	72%	79%
44.3%	57%	47%	51%	60%	66%	19%	47%	53%	51%	41%	41%	34%	41%	26%	60%	54%	46%	17%	27%	46%	47%
73.0%	83%	91%	88%	88%	73%	64%	88%	69%	74%	61%	83%	66%	56%	66%	73%	78%	66%	62%	83%	55%	66%
75.5%	68%	74%	77%	77%	90%	71%	100%	86%	74%	71%	68%	70%	88%	68%	75%	70%	76%	74%	64%	74%	71%
51.3%	47%	54%	50%	50%	50%	48%	56%	48%	56%	45%	47%	56%	46%	49%	54%	56%	55%	54%	54%	51%	52%
82.9%	85%	81%	88%	76%	88%	78%	85%	77%	88%	85%	77%	60%	85%	77%	88%	77%	93%	88%	85%	88%	92%
49.0%	51%	50%	44%	55%	44%	53%	47%	54%	44%	47%	54%	69%	47%	54%	47%	51%	41%	48%	47%	41%	41%
73.5%	74%	76%	74%	76%	66%	67%	80%	78%	76%	87%	76%	76%	74%	56%	75%	79%	74%	71%	56%	52%	100%
66.5%	70%	75%	65%	65%	41%	87%	51%	87%	72%	65%	70%	41%	87%	76%	62%	58%	60%	76%	53%	75%	61%
60.6%	61%	63%	62%	62%	63%	48%	67%	66%	59%	68%	59%	61%	59%	52%	58%	64%	64%	53%	47%	73%	63%
74.3%	76%	86%	76%	76%	73%	65%	86%	79%	74%	62%	73%	87%	66%	73%	77%	87%	73%	69%	62%	81%	60%
59.9%	65%	63%	65%	65%	57%	68%	69%	65%	61%	78%	65%	48%	65%	57%	71%	65%	53%	36%	54%	52%	36%
53.4%	59%	60%	50%	50%	54%	50%	61%	49%	59%	53%	61%	50%	61%	53%	59%	50%	53%	44%	46%	50%	50%
90.0%	88%	89%	88%	84%	96%	85%	92%	85%	96%	92%	85%	67%	92%	85%	100%	100%	79%	96%	92%	100%	100%
63.0%	64%	68%	60%	63%	63%	54%	67%	75%	74%	57%	61%	63%	60%	67%	70%	70%	67%	38%	59%	61%	63%
83.4%	90%	80%	84%	84%	90%	84%	90%	75%	84%	90%	75%	91%	82%	75%	88%	83%	75%	77%	81%	84%	90%
64.6%	52%	67%	69%	61%	62%	58%	69%	58%	67%	58%	75%	68%	69%	68%	67%	69%	63%	72%	68%	58%	58%

Model Similarity Dendrogram

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