	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 78.4%	5th 77.1%	7th 76.2%	2nd 77.8%	4th 77.3%	17th 71.4%	9th 75.6%	3rd 77.5%	8th 76.1%	13th 73.7%	14th 73.1%	11th 74.1%	12th 73.9%	15th 72.8%	10th 74.9%	6th 76.5%	20th 69.2%	16th 71.6%	19th 70.5%	18th 71.2%	21st 68.4%
80.5%	84%	76%	72%	75%	90%	69%	77%	81%	84%	84%	87%	89%	82%	75%	83%	85%	71%	92%	75%		78%
76.9%	77%	78%	78%	78%	67%	83%	72%	80%	64%	69%	84%	88%	75%	92%	68%	64%	86%	73%	89%	77%	73%
71.6%	72%	72%	67%	67%	70%	90%	76%	76%	67%	71%	59%	78%	72%	76%	74%	75%	70%	74%	59%	67%	72%
53.0%	58%	66%	57%	56%	51%	61%	53%	53%	60%	40%	52%	54%	52%	62%	51%	46%	43%	52%	66%	42%	38%
86.1%	85%	85%	85%	80%	88%	76%	83%	88%	90%	83%	83%	89%	90%	88%	87%	89%	95%	92%	83%	88%	82%
79.9%	82%	86%	85%	89%	87%	71%	82%	76%	90%	75%	74%	70%	77%	70%	81%	84%	73%	86%	71%	84%	84%
80.4%	83%	77%	80%	91%	85%	86%	82%	93%	83%	83%	80%	82%	79%	76%	81%	83%	76%	76%	81%	61%	71%
62.5%	71%	64%	62%	66%	69%	45%	67%	63%	62%	63%	62%	80%	61%	63%	58%	68%	62%	59%	52%	62%	53%
69.0%	71%	63%	61%	70%	74%	59%	69%	72%	68%	70%	69%	73%	71%	68%	64%	80%	76%	69%	66%	78%	58%
50.8%	56%	63%	53%	52%	61%	65%	55%	52%	63%	41%	50%	51%	47%	47%	44%	44%	36%	48%	63%	45%	30%
86.1%	91%	88%	91%	91%	82%	93%	87%	90%	84%	87%	94%	72%	86%	87%	90%	87%	87%	64%	90%	84%	84%
40.6%	49%	55%	47%	47%	53%	47%	35%	39%	36%	30%	42%	41%	39%	39%	34%	44%	30%	39%	55%	25%	26%
86.8%	95%	91%	89%	89%	89%	84%	85%	92%	87%	89%	86%	81%	88%	88%	82%	90%	87%	82%	86%	82%	81%
88.7%	90%	88%	82%	90%	88%	94%	85%	90%	91%	95%	92%	94%	88%	88%	90%	93%	88%	80%	85%	83%	88%
85.1%	84%	87%	91%	91%	84%	82%	92%	84%	88%	86%	87%	88%	89%	83%	88%	85%	83%	81%	73%	83%	78%
69.4%	75%	76%	70%	81%	78%	54%	72%	70%	74%	66%	66%	71%	68%	65%	65%	77%	58%	73%	58%	75%	66%
68.0%	71%	73%	74%	78%	72%	74%	69%	74%	70%	67%	63%	70%	53%	55%	86%	74%	59%	59%	58%	63%	67%
60.0%	66%	64%	62%	67%	63%	40%	56%	71%	66%	58%	56%	71%	63%	52%	60%	69%	49%	51%	55%	64%	56%
67.0%	76%	74%	67%	69%	56%	56%	77%	64%	65%	65%	63%	68%	71%	75%	62%	63%	65%	68%	68%	81%	53%
79.1%	84%	68%	77%	77%	90%	91%	82%	86%	81%	80%	80%	80%	77%	80%	73%	78%	77%	72%	75%	77%	76%
79.8%	84%	87%	87%	82%	78%	63%	92%	90%	86%	79%	77%	81%	77%	77%	85%	87%	73%	70%	65%	80%	76%
80.4%	85%	82%	83%	83%	82%	54%	89%	84%	88%	83%	73%	87%	84%	73%	85%	82%	79%	81%	72%	81%	78%
57.8%	72%	56%	67%	72%	65%	66%	59%	65%	56%	51%	48%	44%	50%	69%	62%	63%	36%	59%	73%	38%	43%
85.7%	84%	90%	87%	88%	91%	79%	90%	87%	91%	84%	82%	89%	86%	85%	81%	89%	83%	84%	81%	84%	84%
85.4%	91%	89%	83%	87%	88%	90%	87%	87%	88%	86%	87%	79%	86%	87%	90%	90%	80%	77%	78%	84%	80%
76.7%	83%	75%	74%	73%	81%	71%	71%	71%	74%	81%	80%	67%	77%	78%	81%	79%	77%	79%	80%	77%	82%
71.2%	78%	76%	76%	76%	80%	53%	70%	75%	75%	71%	67%	74%	70%	68%	73%	74%	59%	69%	62%	76%	74%
73.5%	78%	83%	79%	84%	90%	62%	81%	87%	79%	80%	67%	72%	67%	58%	84%	78%	57%	69%	61%	70%	58%
39.0%	51%	48%	45%	50%	45%	45%	42%	41%	40%	30%	37%	29%	36%	48%	44%	35%	28%	26%	40%	40%	18%
64.0%	57%	66%	62%	67%	65%	63%	54%	65%	66%	64%	65%	71%	63%	56%	64%	66%	71%	75%	69%	59%	55%
87.3%	91%	87%	90%	93%	88%	80%	78%	93%	92%	93%	89%	86%	90%	85%	92%	91%	89%	77%	81%	84%	85%
88.5%	88%	88%	93%	93%	91%	70%	84%	84%	93%	89%	98%	82%	89%	84%	87%	85%	91%	86%	98%	95%	90%
59.6%	60%	61%	56%	56%	58%	78%	64%	64%	56%	60%	48%	66%	60%	64%	60%	58%	58%	62%	48%	56%	58%
79.2%	87%	77%	86%	80%	89%	80%	82%	83%	80%	88%	71%	86%	85%	63%	82%	88%	63%	70%	67%	88%	69%
58.0%	68%	68%	60%	60%	46%	56%	56%	62%	60%	58%	55%	61%	61%	71%	48%	53%	55%	54%	75%	46%	44%
77.3%	85%	87%	83%	85%	68%	85%	83%	91%	71%	77%	84%	72%	80%	68%	75%	80%	67%	70%	63%	70%	80%
82.7%	84%	88%	89%	89%	84%	77%	89%	86%	84%	83%	87%	79%	78%	81%	83%	88%	77%	88%	75%	77%	70%
91.4%	90%	90%	98%	96%	94%	97%	93%	93%	92%	93%	98%	74%	98%	90%	98%	95%	88%	88%	86%	81%	87%
78.7%	88%	81%	85%	87%	92%	67%	87%	81%	85%	83%	77%	66%	79%	68%	86%	91%	62%	82%	55%	68%	83%
91.4%	94%	94%	89%	89%	91%	88%	97%	97%	89%	93%	80%	100%	93%	97%	93%	90%	91%	95%	80%	89%	91%
83.4%	88%	83%	95%	96%	94%	72%	94%	91%	91%	89%	76%	75%	84%	64%	96%	89%	75%	73%	58%	84%	85%
76.1%	79%	84%	77%	73%	84%	71%	78%	79%	78%	75%	82%	78%	81%	82%	66%	76%	69%	69%	75%	70%	72%
80.9%	88%	81%	84%	84%	81%	82%	75%	82%	84%	78%	87%	80%	76%	87%	85%	83%	76%	87%	80%	73%	65%

Model Similarity Dendrogram

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