	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
Score	2nd 78.4%	4th 76.7%	3rd 77.1%	1st 78.5%	11th 73.7%	17th 69.3%	10th 73.8%	15th 71.8%	14th 72.7%	12th 73.6%	7th 75.7%	18th 69.0%	9th 73.9%	8th 74.8%	6th 75.7%	5th 75.8%	16th 69.4%	19th 68.3%	13th 73.1%	20th 67.8%	21st 63.1%
83.2%	91%	91%	81%	95%	73%	69%	90%	80%	89%	82%	86%	80%	87%	85%	87%	91%	82%	71%	92%	77%	68%
79.2%	84%	80%	84%	84%	64%	81%	83%	79%	64%	87%	83%	81%	81%	81%	86%	81%	84%	81%	82%	76%	58%
74.5%	79%	66%	79%	79%	59%	75%	69%	75%	59%	82%	82%	82%	82%	76%	79%	72%	72%	76%	70%	59%	92%
72.4%	73%	69%	74%	71%	74%	63%	76%	77%	78%	73%	73%	74%	74%	75%	75%	75%	68%	70%	63%
82.0%	92%	80%	94%	97%	81%	91%	93%	80%	81%	84%	81%	77%	84%	75%	83%	74%	71%	61%	94%	79%	71%
91.0%	94%	95%	94%	94%	96%	95%	96%	90%	96%	94%	96%	91%	99%	85%	91%	89%	92%	92%	91%	94%	46%
73.3%	81%	79%	73%	74%	80%	62%	74%	79%	75%	69%	79%	71%	76%	86%	62%	80%	68%	85%	74%	55%	57%
74.9%	91%	78%	79%	83%	65%	55%	83%	80%	73%	69%	78%	71%	82%	71%	89%	74%	72%	60%	70%	71%	79%
77.9%	82%	80%	76%	76%	73%	75%	80%	91%	73%	82%	82%	83%	74%	71%	70%	76%	77%	85%	76%	94%	59%
78.8%	77%	84%	80%	84%	80%	82%	68%	74%	78%	75%	82%	74%	75%	90%	84%	84%	66%	64%	92%		83%
69.9%	74%	74%	75%	75%	79%	68%	71%	68%	65%	72%	75%	72%	68%	75%	63%	69%	62%	56%	68%	62%	77%
76.7%	85%	77%	73%	79%	80%	79%	75%	77%	73%	78%	80%	78%	75%	76%	80%	74%	76%	66%	71%	78%	81%
69.2%	72%	72%	70%	86%	71%	76%	58%	62%	70%	79%	77%	44%	71%	79%	75%	72%	60%	54%	80%	55%
59.7%	70%	68%	68%	73%	71%	49%	70%	65%	64%	52%	68%	41%	63%	76%	59%	57%	58%	51%	60%	36%	35%
59.8%	64%	65%	69%	66%	52%	53%	67%	70%	66%	58%	54%	61%	63%	60%	58%	59%	65%	47%	54%	48%	56%
64.8%	69%	71%	72%	77%	79%	50%	64%	66%	66%	62%	60%	66%	68%	70%	70%	78%	52%	62%	64%	46%	48%
80.2%	86%	90%	84%	77%	80%	71%	76%	61%	79%	78%	79%	60%	76%	75%	87%	96%	93%	79%	86%	86%	86%
57.2%	65%	59%	60%	63%	63%	44%	54%	43%	54%	44%	56%	67%	51%	56%	51%	66%	71%	51%	62%	64%
68.9%	85%	56%	87%	82%	85%	56%	70%	70%	64%	68%	68%	62%	63%	65%	87%	79%	62%	65%	50%	73%	49%
72.5%	85%	76%	84%	81%	76%	78%	84%	61%	64%	74%	78%	65%	70%	76%	78%	77%	51%	67%	78%		47%
69.8%	68%	68%	82%	77%	77%	69%	73%	60%	67%	80%	74%	65%	69%	83%	66%	70%	51%	65%	73%	65%	63%
81.3%	74%	79%	79%	83%	86%	84%	86%	84%	85%	80%	89%	72%	87%	93%	90%	90%	79%	74%	87%	73%	54%
78.1%	77%	77%	85%	79%	85%	83%	75%	77%	82%	73%	81%	77%	81%	82%	76%	77%	79%	70%	73%	74%	77%
62.8%	79%	75%	65%	78%	65%	70%	49%	58%	62%	75%	75%	45%	66%	55%	75%	71%	55%	47%	69%	59%	26%
63.7%	68%	72%	67%	69%	76%	62%	61%	58%	62%	56%	75%	53%	59%	75%	54%	59%	54%	70%	72%	66%	49%
56.9%	55%	67%	63%	66%	64%	64%	60%	49%	56%	64%	67%	44%	50%	68%	48%	51%	45%	55%	63%	70%	25%
63.9%	74%	68%	66%	69%	66%	50%	64%	59%	68%	59%	62%	68%	71%	68%	73%	71%	66%	69%	62%	44%	44%
68.6%	76%	70%	66%	72%	86%	40%	64%	71%	76%	65%	74%	64%	73%	50%	85%	74%	69%	75%	53%	67%	71%
76.1%	77%	79%	85%	85%	77%	75%	79%	74%	79%	75%	79%	70%	75%	72%	73%	80%	70%	73%	73%	74%	75%
73.4%	85%	84%	81%	83%	83%	59%	67%	82%	78%	68%	80%	63%	69%	53%	72%	80%	77%	73%	71%	62%	71%
75.2%	84%	80%	85%	85%	82%	74%	80%	68%	75%	82%	71%	72%	77%	77%	85%	74%	68%	55%	74%	68%	64%
68.7%	69%	75%	62%	62%	82%	66%	72%	66%	82%	59%	59%	59%	59%	65%	75%	69%	69%	65%	71%	82%	75%
72.4%	72%	66%	79%	79%	59%	75%	69%	75%	59%	82%	82%	82%	82%	76%	69%	72%	72%	76%	70%	66%	59%
78.4%	91%	90%	86%	79%	64%	63%	90%	87%	93%	77%	80%	64%	75%	89%	90%	97%	78%	90%	64%	47%	52%
75.4%	88%	81%	78%	80%	37%	94%	70%	81%	70%	81%	74%	69%	85%	86%	64%	71%	73%	83%	58%	81%	79%
61.6%	68%	67%	68%	62%	49%	65%	63%	65%	59%	65%	61%	64%	68%	60%	53%	67%	58%	53%	62%	56%	61%
78.4%	86%	80%	85%	91%	79%	74%	83%	67%	78%	89%	78%	77%	84%	78%	83%	81%	71%	62%	75%	76%	69%
86.4%	90%	92%	86%	86%	83%	91%	80%	96%	90%	86%	86%	76%	90%	88%	99%	91%	71%	75%	99%	74%
71.2%	78%	76%	78%	84%	72%	66%	71%	70%	67%	82%	70%	69%	71%	72%	78%	79%	60%	48%	71%	69%	65%
91.6%	94%	100%	87%	87%	93%	91%	97%	90%	93%	83%	83%	83%	83%	90%	97%	94%	94%	90%	96%	99%	99%
79.0%	80%	84%	88%	82%	73%	67%	78%	80%	75%	86%	82%	78%	82%	79%	84%	75%	79%	80%	76%	73%
61.2%	67%	65%	63%	59%	62%	57%	62%	58%	62%	66%	60%	65%	59%	59%	71%	62%	59%	50%	65%	53%
81.4%	73%	92%		81%	86%		79%	64%	76%	68%	97%	90%	79%	96%	83%	83%	87%	97%	90%	60%	66%

Model Similarity Dendrogram

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