	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 70.2%	4th 70.0%	7th 69.3%	1st 70.5%	9th 68.8%	16th 65.1%	6th 69.5%	10th 68.6%	13th 67.9%	8th 69.2%	12th 67.9%	21st 61.2%	14th 67.5%	15th 65.4%	3rd 70.0%	5th 69.9%	18th 65.0%	19th 62.8%	17th 65.0%	20th 61.8%	11th 67.9%
78.2%	83%	80%	89%	91%	76%	70%	73%	74%	76%	78%	77%	75%	74%	79%	87%	84%	74%	69%	76%	75%	82%
61.8%	68%	61%	70%	69%	45%	72%	65%	64%	55%	64%	62%	60%	64%	64%	66%	67%	54%	49%	57%	60%	61%
49.3%	45%	50%	47%	53%	48%	61%	48%	47%	47%	54%	54%	60%	44%	53%	44%	47%	50%	48%	47%	47%	41%
64.1%	76%	67%	68%	73%	68%	51%	69%	60%	73%	70%	68%	48%	68%	55%	70%	75%	55%	50%	55%	55%	73%
71.9%	76%	75%	78%	78%	77%	70%	74%	76%	75%	79%	64%	64%	64%	65%	71%	75%	64%	69%	64%	72%	79%
86.7%	89%	86%	82%	82%	83%	88%	91%	89%	87%	87%	87%	88%	87%	88%	91%	87%	82%	84%	88%	87%	88%
83.2%	82%	83%	76%	79%	79%	68%	89%	84%	91%	87%	82%	87%	89%	87%	80%	81%	88%	88%	82%	87%	78%
72.1%	70%	74%	69%	66%	75%	64%	80%	78%	79%	76%	76%	74%	76%	70%	72%	77%	73%	60%	67%	73%	65%
81.6%	84%	81%	82%	77%	91%	82%	85%	79%	83%	82%	82%	74%	74%	74%	82%	83%	79%	91%	82%	83%	84%
66.6%	74%	75%	57%	74%	69%	65%	82%	68%	69%	64%	66%	40%	74%	69%	55%	75%	59%	63%	70%	71%	60%
49.7%	51%	52%	54%	60%	54%	69%	53%	60%	46%	45%	52%	31%	48%	39%	50%	49%	49%	22%	54%	44%	62%
71.7%	71%	83%	67%	79%	80%	81%	60%	73%	70%	61%	78%	67%	79%	83%	53%	65%	73%	88%	83%	54%	58%
77.8%	85%	83%	87%	91%	82%	75%	72%	75%	75%	79%	79%	50%	73%	69%	83%	83%	79%	78%	75%	79%	81%
81.3%	81%	81%	74%	87%	78%	74%	87%	76%	79%	87%	78%	78%	79%	87%	86%	85%	85%	68%	87%		89%
76.7%	86%	78%	74%	76%	77%	75%	75%	79%	77%	84%	77%	66%	77%	77%	85%	81%	75%	64%	76%	72%	79%
63.9%	63%	67%	66%	70%	63%	65%	75%	63%	59%	68%	66%	50%	66%	60%	66%	63%	62%	60%	62%	63%	65%
70.7%	73%	75%	75%	75%	91%	76%	69%	50%	72%	65%	76%	76%	58%	60%	76%	79%	60%	70%	76%	58%	74%
58.7%	62%	61%	61%	61%	65%	41%	68%	71%	59%	61%	60%	84%	62%	45%	60%	55%	50%	47%	47%	58%	54%
43.8%	50%	40%	36%	36%	70%	14%	53%	39%	51%	61%	37%	36%	36%	29%	74%	66%	11%	36%	29%	54%	62%
55.0%	61%	59%	64%	64%	43%	60%	56%	46%	52%	55%	55%	50%	60%	55%	59%	60%	53%	44%	52%	53%	55%
63.0%	57%	69%	66%	66%	65%	65%	59%	67%	61%	65%	59%	53%	64%	63%	68%	66%	61%	58%	62%	65%	65%
73.5%	74%	71%	74%	74%	71%	79%	76%	66%	71%	87%	80%	57%	66%	72%	83%	73%	77%	72%	67%	74%	80%
60.1%	66%	62%	60%	56%	65%	67%	56%	65%	58%	60%	60%	45%	56%	60%	68%	64%	58%	61%	60%	60%	56%
61.8%	70%	67%	71%	71%	61%	65%	61%	68%	67%	61%	66%	45%	58%	61%	68%	67%	63%	58%	69%	10%	70%
85.0%	87%	82%	86%	89%	91%	86%	86%	90%	89%	89%	81%	81%	88%	86%	81%	85%	91%	69%	81%		82%
59.2%	56%	64%	63%	59%	59%	74%	59%	47%	58%	60%	60%	52%	50%	65%	62%	62%	60%	51%	68%	52%	63%
58.2%	56%	64%	68%	67%	58%	44%	67%	66%	57%	59%	49%	56%	61%	52%	64%	57%	59%	52%	56%	52%	59%
49.1%	50%	56%	55%	60%	68%	26%	51%	53%	56%	60%	52%	36%	46%	38%	62%	54%	43%	45%	29%	39%	53%
60.0%	72%	75%	63%	75%	56%	61%	73%	69%	51%	48%	75%	36%	52%	63%	51%	59%	66%	69%	83%	10%	54%
77.9%	83%	83%	81%	81%	62%	77%	84%	85%	87%	90%	75%	64%	83%	71%	81%	87%	68%	67%	71%	73%	82%
57.6%	55%	59%	63%	61%	60%	49%	55%	50%	56%	60%	65%	56%	65%	56%	58%	56%	55%	59%	57%	61%	54%
82.3%	84%	81%	85%	84%	84%	69%	84%	85%	85%	77%	76%	70%	88%	78%	88%	82%	80%	84%	85%	88%	92%
49.2%	45%	50%	47%	48%	48%	61%	48%	47%	47%	54%	54%	60%	44%	53%	45%	49%	51%	48%	47%	44%	44%
72.9%	77%	69%	74%	76%	72%	67%	73%	78%	80%	82%	78%	76%	78%	70%	75%	78%	74%	73%	64%	52%	65%
58.7%	63%	63%	60%	55%	48%	56%	47%	59%	58%	51%	55%	55%	74%	65%	59%	63%	62%	59%	63%	67%	51%
59.3%	63%	58%	63%	64%	57%	60%	67%	71%	57%	69%	63%	58%	57%	58%	62%	61%	57%	43%	45%	56%	56%
78.6%	76%	85%	84%	81%	83%	74%	81%	87%	79%	73%	83%	82%	73%	79%	84%	74%	83%	69%	71%	66%	83%
62.3%	74%	64%	63%	65%	65%	60%	68%	65%	68%	65%	65%	48%	65%	48%	75%	65%	55%	66%	52%	48%	65%
53.8%	57%	58%	59%	54%	53%	43%	59%	58%	52%	59%	53%	53%	59%	54%	56%	54%	58%	41%	41%	54%	54%
89.8%	95%	89%	92%	86%	92%	76%	91%	92%	92%	85%	84%	78%	96%	85%	96%	92%	88%	92%	92%	96%	96%
70.5%	71%	72%	74%	68%	70%	65%	71%	73%	71%	63%	63%	68%	75%	68%	71%	70%	66%	76%	62%	93%	71%
80.2%	86%	86%	84%	83%	88%	83%	88%	81%	75%	83%	72%	78%	86%	86%	75%	84%	79%	69%	75%	67%	76%
68.4%	70%	71%	68%	68%	69%	70%	60%	78%	68%	68%	75%	68%	68%	75%	70%	65%	67%	71%	68%	61%	58%

Model Similarity Dendrogram

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