	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	1st 76.3%	4th 75.2%	5th 74.8%	2nd 76.2%	12th 72.2%	17th 70.0%	11th 72.3%	8th 74.1%	15th 70.7%	6th 74.2%	9th 73.6%	20th 67.3%	7th 74.2%	14th 71.9%	21st 64.2%	3rd 75.8%	10th 72.4%	19th 69.1%	18th 70.0%	16th 70.3%	13th 72.0%
82.0%	85%	84%	77%	81%	88%	67%	86%	87%	75%	81%	92%	84%	88%	84%	83%	86%	82%	73%	69%	91%	79%
74.2%	82%	74%	72%	76%	56%	77%	68%	69%	52%	74%	66%	88%	75%	69%	84%	77%	84%	71%	91%	75%	79%
85.4%	86%	86%	89%	86%	80%	98%	86%	93%	80%	91%	91%	85%	86%	86%	85%	88%	85%	84%	77%	76%	76%
45.0%	48%	56%	48%	39%	53%	46%	45%	49%	48%	38%	52%	12%	59%	54%	0%	47%	55%	40%	56%	48%	51%
82.1%	83%	87%	87%	87%	80%	79%	80%	70%	78%	74%	81%	81%	83%	93%	97%	89%	84%	75%	86%	72%	78%
84.8%	86%	81%	81%	84%	88%	95%	91%	84%	94%	92%	91%	93%	90%	81%	0%	88%	97%	82%	94%	94%	95%
77.8%	78%	73%	81%	81%	86%	82%	77%	77%	77%	87%	81%	71%	81%	77%	80%	82%	78%	77%	61%	73%	73%
70.3%	79%	73%	73%	74%	79%	68%	72%	73%	65%	81%	71%	69%	71%	68%	74%	76%	69%	59%	55%	62%	66%
82.0%	78%	77%	87%	80%	91%	80%	98%	76%	87%	78%	78%	75%	78%	76%	84%	73%	80%	85%	89%	81%	90%
38.9%	40%	47%	36%	44%	44%	41%	32%	37%	45%	33%	45%	9%	42%	47%	37%	39%	47%	48%	49%	27%	28%
87.0%	91%	91%	91%	90%	90%	87%	90%	89%	79%	90%	89%	94%	93%	89%	92%	96%	71%	48%	88%	85%	95%
40.3%	51%	56%	40%	50%	43%	34%	25%	40%	39%	30%	42%	21%	39%	38%	42%	62%	39%	43%	40%	38%	34%
75.5%	74%	81%	83%	85%	72%	77%	61%	77%	68%	75%	79%	56%	78%	78%	83%	76%	65%	73%	79%	82%	83%
85.5%	89%	92%	84%	81%	83%	74%	86%	90%	85%	76%	84%	90%	89%	86%	92%	96%	74%	75%	88%	88%	93%
79.0%	88%	78%	87%	88%	78%	79%	84%	87%	74%	84%	77%	74%	80%	77%	76%	80%	79%	69%	68%	77%	74%
85.9%	91%	87%	91%	90%	86%	72%	87%	85%	83%	92%	87%	85%	84%	85%	93%	90%	85%	84%	74%	83%	90%
78.0%	81%	82%	82%	87%	82%	81%	75%	64%	82%	79%	80%	74%	75%	80%	87%	83%	77%	71%	65%	73%	79%
63.4%	72%	71%	63%	68%	65%	47%	59%	63%	59%	66%	70%	64%	61%	65%	56%	67%	70%	51%	62%	64%	69%
66.9%	68%	69%	64%	71%	57%	53%	80%	72%	67%	71%	64%	58%	72%	68%	69%	69%	74%	68%	69%	62%	60%
83.1%	86%	74%	77%	83%	91%	94%	86%	94%	86%	94%	86%	86%	80%	79%	83%	76%	77%	83%	72%	87%	71%
71.9%	79%	71%	80%	80%	71%	71%	75%	82%	66%	83%	69%	70%	73%	64%	76%	75%	68%	60%	60%	65%	71%
77.7%	86%	83%	86%	83%	77%	77%	81%	80%	82%	81%	77%	70%	78%	71%	80%	83%	75%	71%	66%	70%	75%
69.3%	74%	69%	76%	92%	63%	59%	68%	69%	73%	77%	69%	35%	72%	67%	73%	76%	51%	67%	71%	81%	73%
70.1%	80%	80%	81%	81%	72%	72%	69%	79%	74%	82%	69%	59%	76%	73%	77%	77%	62%	52%	69%	10%	79%
74.6%	77%	72%	72%	75%	71%	77%	70%	69%	74%	71%	73%	72%	74%	72%	75%	77%	78%	80%	83%	75%	80%
73.0%	75%	71%	77%	79%	78%	67%	68%	63%	70%	80%	78%	72%	71%	70%	83%	75%	67%	66%	70%	76%	78%
66.4%	73%	67%	67%	66%	63%	50%	67%	73%	65%	69%	60%	70%	69%	53%	75%	68%	75%	64%	65%	65%	70%
86.0%	91%	92%	90%	96%	95%	73%	88%	96%	76%	93%	87%	78%	90%	80%	87%	91%	86%	83%	63%	86%	85%
45.6%	51%	60%	48%	48%	34%	30%	41%	60%	42%	37%	57%	6%	44%	40%	45%	58%	51%	51%	44%	52%	59%
56.1%	62%	62%	59%	63%	52%	53%	43%	45%	55%	56%	67%	54%	48%	55%	59%	63%	61%	61%	54%	64%	42%
76.0%	78%	77%	76%	81%	75%	72%	81%	80%	75%	76%	77%	77%	78%	70%	78%	78%	73%	71%	70%	78%	74%
60.3%	66%	62%	60%	62%	68%	51%	62%	56%	68%	57%	57%	64%	62%	62%	0%	61%	66%	64%	76%	72%	71%
60.1%	61%	61%	64%	61%	55%	73%	61%	67%	55%	66%	66%	60%	61%	61%	57%	61%	58%	59%	48%	55%	53%
74.3%	79%	69%	79%	89%	88%	81%	81%	82%	87%	89%	83%	64%	77%	70%	0%	83%	86%	81%	61%	65%	66%
54.6%	56%	71%	56%	57%	38%	47%	41%	50%	50%	58%	57%	41%	63%	68%	50%	54%	65%	54%	71%	63%	36%
69.1%	72%	77%	76%	72%	55%	75%	76%	81%	55%	68%	57%	73%	65%	72%	58%	67%	74%	68%	69%	72%	70%
79.8%	81%	73%	84%	80%	80%	80%	82%	68%	78%	75%	66%	78%	84%	92%	80%	82%	70%	70%	91%	89%	93%
78.0%	95%	83%	85%	83%	83%	95%	91%	89%	82%	85%	76%	69%	87%	76%	0%	83%	76%	80%	76%	64%	80%
82.0%	84%	84%	81%	84%	82%	82%	82%	87%	81%	86%	82%	83%	85%	74%	87%	88%	80%	81%	75%	77%	77%
90.4%	96%	97%	94%	96%	97%	84%	96%	90%	97%	91%	91%	98%	96%	96%	0%	95%	98%	98%	95%	95%	98%
77.5%	79%	79%	80%	81%	74%	79%	76%	79%	65%	78%	82%	86%	79%	81%	78%	75%	81%	82%	71%	69%	74%
73.0%	75%	78%	71%	70%	70%	58%	71%	83%	71%	73%	82%	76%	79%	76%	72%	76%	76%	76%	62%	73%	64%
72.6%	75%	75%	80%	72%	72%	72%	72%	82%	75%	72%	78%	68%	74%	69%	73%	75%	66%	74%	66%	67%	67%

Model Similarity Dendrogram

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