	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	3rd 74.7%	6th 72.7%	7th 72.2%	1st 75.7%	2nd 74.8%	21st 60.8%	13th 70.8%	10th 71.7%	11th 70.8%	5th 73.3%	12th 70.8%	15th 69.8%	9th 71.9%	14th 70.4%	8th 71.9%	4th 73.5%	18th 66.6%	16th 66.7%	17th 66.6%	20th 65.1%	19th 66.0%
71.7%	81%	77%	69%	80%	85%	46%	68%	66%	68%	79%	68%	73%	72%	79%	74%	72%	65%	82%	55%	80%	66%
75.1%	75%	72%	77%	77%	61%	73%	74%	90%	71%	67%	78%	88%	76%	93%	68%	72%	79%	62%	91%	62%	71%
69.0%	64%	66%	74%	75%	83%	71%	68%	74%	68%	80%	74%	68%	66%	66%	74%	74%	63%	60%	58%	56%	66%
48.4%	52%	49%	43%	55%	56%	48%	46%	55%	50%	49%	56%	48%	54%	66%	42%	45%	37%	40%	59%	37%	30%
78.7%	79%	87%	79%	79%	78%	73%	72%	69%	79%	79%	88%	91%	84%	88%	75%	84%	68%	70%	88%	77%	65%
74.6%	75%	77%	81%	80%	81%	61%	78%	70%	79%	82%	71%	79%	80%	71%	78%	76%	68%	76%	65%	63%	75%
86.0%	88%	85%	89%	87%	90%	81%	86%	85%	88%	88%	80%	91%	89%	79%	86%	89%	91%	78%	85%	85%	87%
49.8%	66%	49%	50%	63%	57%	22%	50%	54%	48%	65%	46%	52%	53%	41%	63%	61%	37%	49%	26%	53%	41%
75.4%	83%	77%	73%	81%	75%	53%	70%	77%	72%	82%	78%	80%	78%	85%	79%	85%	81%	70%	67%	79%	58%
41.4%	46%	45%	34%	57%	52%	36%	42%	48%	43%	49%	48%	28%	51%	48%	37%	34%	40%	25%	51%	33%	23%
81.8%	82%	85%	81%	84%	83%	82%	82%	73%	88%	90%	84%	87%	87%	87%	82%	86%	80%	68%	82%	84%	60%
40.7%	54%	49%	41%	52%	50%	30%	41%	51%	43%	41%	50%	28%	38%	50%	31%	38%	29%	22%	53%	46%	18%
79.0%	89%	72%	87%	95%	85%	57%	89%	84%	79%	86%	70%	84%	80%	71%	84%	82%	67%	76%	61%	74%	88%
84.8%	85%	85%	86%	75%	81%	87%	94%	82%	87%	73%	87%	81%	85%	95%	89%	80%	81%	82%	95%	85%	86%
87.2%	92%	94%	90%	82%	93%	72%	90%	87%	90%	98%	87%	82%	93%	87%	88%	95%	79%	77%	82%	81%	92%
69.0%	79%	73%	69%	83%	79%	50%	61%	68%	68%	72%	66%	61%	68%	66%	74%	82%	64%	68%	55%	73%	71%
56.1%	62%	62%	62%	66%	71%	46%	48%	50%	55%	62%	48%	46%	46%	46%	74%	63%	51%	42%	60%	55%	63%
58.3%	67%	59%	58%	83%	59%	34%	50%	60%	58%	61%	58%	58%	57%	53%	65%	66%	48%	60%	48%		64%
63.7%	63%	72%	65%	61%	61%	43%	80%	65%	68%	74%	57%	68%	68%	67%	73%	78%	74%	72%	64%	0%	64%
82.3%	86%	77%	85%	84%	82%	86%	89%	84%	81%	81%	79%	86%	88%	80%	87%	88%	84%	67%	69%	85%	80%
74.6%	88%	78%	81%	81%	80%	41%	78%	82%	79%	85%	75%	84%	81%	63%	84%	89%	54%	75%	48%	57%	84%
73.6%	83%	78%	80%	87%	87%	48%	85%	68%	73%	89%	66%	67%	83%	68%	73%	86%	60%	78%	53%	57%	77%
66.7%	77%	68%	77%	76%	65%	59%	66%	72%	56%	63%	63%	50%	62%	70%	72%	64%	68%	68%	79%	70%	56%
74.6%	77%	71%	78%	76%	83%	72%	80%	83%	82%	76%	74%	75%	75%	74%	77%	78%	70%	66%	60%	67%	72%
82.3%	82%	93%	80%	77%	80%	83%	92%	82%	81%	76%	85%	78%	84%	83%	77%	77%	77%	85%	89%	85%	82%
71.5%	83%	70%	71%	76%	76%	54%	67%	62%	74%	74%	76%	75%	74%	70%	75%	75%	71%	75%	67%	66%	70%
77.6%	86%	79%	79%	88%	81%	57%	73%	84%	80%	82%	67%	79%	79%	61%	83%	85%	68%	85%	62%	84%	88%
65.5%	68%	68%	66%	78%	84%	43%	65%	72%	75%	79%	56%	63%	66%	51%	75%	77%	58%	64%	52%	52%	64%
47.8%	44%	49%	52%	59%	54%	28%	51%	53%	34%	38%	65%	30%	51%	52%	57%	61%	52%	59%	52%	30%	33%
60.9%	63%	65%	64%	71%	86%	56%	46%	49%	62%	56%	67%	58%	49%	58%	60%	65%	62%	74%	62%	55%	50%
68.3%	70%	68%	62%	46%	68%	88%	70%	71%	69%	54%	68%	78%	67%	82%	45%	53%	81%	76%	85%	79%	54%
76.1%	77%	80%	71%	70%	62%	75%	78%	71%	78%	65%	71%	78%	80%	80%	71%	73%	78%	86%	88%	91%	75%
69.2%	68%	66%	74%	75%	83%	71%	68%	74%	68%	80%	74%	68%	66%	66%	72%	67%	68%	60%	58%	60%	68%
79.4%	83%	76%	80%	81%	82%	76%	84%	82%	78%	86%	80%	80%	80%	74%	79%	83%	79%	77%	69%	78%	80%
46.9%	54%	57%	47%	62%	37%	42%	39%	44%	43%	46%	48%	48%	54%	64%	37%	37%	41%	50%	56%	50%	29%
72.8%	78%	79%	79%	76%	69%	64%	80%	82%	70%	78%	76%	67%	76%	68%	70%	78%	69%	70%	59%	68%	72%
82.5%	89%	87%	82%	80%	88%	90%	89%	83%	89%	73%	87%	77%	84%	87%	71%	75%	84%	75%	74%	79%	90%
83.2%	71%	87%	82%	91%	83%	83%	82%	73%	84%	78%	86%	93%	81%	87%	81%	84%	89%	81%	99%	75%	78%
64.3%	74%	69%	73%	73%	71%	47%	68%	70%	67%	77%	62%	67%	73%	51%	77%	76%	57%	54%	52%	45%	48%
86.2%	81%	83%	92%	93%	98%	88%	85%	92%	85%	98%	92%	85%	83%	83%	85%	92%	85%	76%	74%	72%	88%
70.8%	75%	73%	77%	80%	83%	70%	76%	78%	76%	79%	71%	71%	73%	62%	80%	76%	62%	22%	54%	74%	75%
75.1%	80%	81%	73%	69%	78%	55%	69%	78%	78%	82%	81%	76%	80%	79%	82%	79%	62%	78%	77%	66%	74%
80.0%	91%	89%	91%	90%	78%	72%	74%	84%	81%	78%	81%	74%	76%	77%	87%	79%	81%	86%	80%	66%	64%

Model Similarity Dendrogram

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