	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 82.3%	8th 75.7%	7th 78.7%	2nd 81.3%	5th 78.8%	21st 58.0%	12th 72.9%	9th 74.9%	13th 72.5%	6th 78.8%	14th 72.4%	20th 67.0%	10th 74.0%	16th 70.8%	4th 78.9%	3rd 79.7%	17th 70.6%	11th 73.7%	19th 67.5%	18th 70.1%	15th 71.3%
74.3%	94%	82%	93%	94%	94%	49%	70%	66%	63%	81%	66%	56%	82%	58%	77%	87%	79%	73%	61%	70%	65%
76.5%	80%	80%	86%	84%	66%	92%	71%	78%	72%	67%	83%	81%	83%	81%	74%	62%	76%	60%	81%	79%	70%
80.1%	89%	83%	89%	89%	81%	10%	74%	87%	77%	99%	89%	77%	84%	83%	85%	81%	80%	86%	74%	75%	91%
86.5%	89%	83%	88%	85%	88%	88%	90%	86%	86%	89%	85%	87%	89%	87%	88%	85%	82%	87%	83%	87%	84%
81.0%	84%	87%	74%	74%	81%	72%	70%	87%	80%	88%	86%	88%	80%	80%	93%	87%	79%	88%	87%	70%	65%
65.8%	74%	67%	71%	76%	71%	64%	62%	64%	61%	75%	67%	46%	67%	54%	69%	71%	64%	69%	63%	56%	70%
65.0%	75%	60%	73%	91%	72%	47%	64%	72%	80%	72%	62%	68%	54%	71%	59%	76%	30%	73%	49%	62%	54%
71.2%	84%	70%	66%	86%	68%	35%	70%	79%	77%	83%	63%	71%	72%	60%	83%	91%	84%		39%	62%	81%
69.2%	79%	81%	69%	82%	76%	37%	51%	72%	54%	81%	73%	37%	72%	69%	87%	87%	88%	83%	50%	63%	62%
82.7%	86%	86%	82%	88%	86%	97%	82%	74%	83%	85%	84%	86%	82%	79%	80%	82%	75%	84%	84%	73%	79%
79.9%	86%	92%	77%	85%	80%	92%	86%	88%	83%	74%	87%	86%	77%	71%	85%	82%	74%	59%	77%	83%	53%
84.6%	91%	89%	89%	93%	90%	89%	83%	91%	80%	90%	73%	91%	80%	73%	89%	86%	75%		79%	70%	91%
80.4%	86%	74%	86%	90%	71%	74%	86%	86%	75%	84%	76%	82%	80%	80%	85%	86%	80%		65%	75%	86%
78.4%	88%	81%	80%	83%	74%	64%	87%	82%	83%	75%	85%	59%	69%	90%	73%	82%	67%	87%	88%	86%	63%
83.2%	81%	90%	86%	67%	90%	89%	75%	68%	80%	80%	92%	69%	80%	87%	96%	91%	87%	74%	89%	87%	90%
71.8%	90%	82%	83%	91%	83%	41%	67%	64%	62%	90%	63%	60%	74%	64%	79%	88%	64%		55%	81%	55%
58.9%	66%	79%	88%	65%	76%	48%	59%	50%	47%	71%	50%	47%	49%	46%	70%	77%	42%	37%	62%	42%	65%
58.4%	78%	54%	75%	79%	71%	33%	49%	70%	43%	65%	41%	40%	60%	44%	79%	64%	66%		45%	46%	65%
66.0%	70%	63%	69%	64%	72%	53%	86%	69%	70%	65%	67%	39%	64%	64%	75%	79%	64%	60%	60%	74%	60%
69.0%	82%	46%	71%	79%	73%	58%	66%	93%	74%	80%	58%	55%	58%	63%	68%	73%	75%	90%	61%	53%	72%
78.3%	90%	78%	79%	89%	85%	52%	76%	89%	75%	89%	72%	80%	69%	59%	89%	93%	81%	87%	55%	72%	85%
80.3%	92%	70%	79%	90%	85%	50%	83%	78%	82%	90%	74%	90%	79%	74%	88%	92%	79%	89%	59%	85%	79%
74.7%	70%	73%	74%	73%	79%	89%	86%	88%	69%	67%	85%	59%	72%	89%	73%	70%	72%	65%	73%	70%	73%
79.1%	88%	70%	87%	88%	84%	70%	85%	84%	81%	78%	71%	76%	79%	77%	88%	88%	68%	79%	61%	75%	85%
73.4%	84%	76%	84%	74%	87%	65%	82%	76%	79%	71%	80%	61%	61%	83%	68%	76%	56%		80%	67%	58%
70.9%	72%	74%	78%	70%	82%	60%	69%	65%	72%	72%	70%	70%	76%	66%	71%	76%	72%	73%	73%	78%	50%
67.1%	83%	65%	80%	86%	71%	36%	52%	62%	54%	83%	43%	58%	76%	52%	86%	77%	69%	90%	53%	61%	72%
74.8%	84%	78%	73%	88%	87%	52%	85%	85%	83%	88%	71%	68%	78%	61%	92%	90%	45%		47%	69%	71%
69.8%	86%	85%	86%	86%	84%	63%	69%	62%	62%	61%	70%	59%	69%	62%	73%	72%	61%	59%	63%	62%	71%
61.0%	71%	61%	61%	80%	86%	40%	45%	59%	64%	74%	51%	40%	66%	70%	65%	65%	68%		55%	58%	40%
74.3%	80%	78%	80%	67%	72%	81%	73%	59%	71%	58%	84%	70%	73%	82%	65%	73%	79%	78%	78%	77%	82%
73.9%	76%	77%	71%	71%	79%	10%	86%	73%	83%	61%	71%	83%	75%	76%	74%	77%	78%	74%	86%	85%	85%
66.3%	67%	70%	76%	76%	68%	10%	62%	74%	64%	85%	76%	64%	71%	70%	65%	69%	69%	72%	61%	62%	62%
71.2%	83%	66%	75%	92%	90%	51%	77%	78%	70%	92%	66%	42%	61%	60%	90%	79%	72%	71%	47%	41%	93%
59.5%	83%	69%	68%	87%	23%	51%	42%	63%	65%	82%	47%	37%	64%	56%	63%	46%	51%	53%	78%	86%	35%
75.3%	86%	72%	82%	87%	78%	65%	80%	83%	75%	89%	79%	62%	84%	61%	83%	81%	62%	69%	51%		76%
82.9%	94%	88%	87%	73%	94%	88%	80%	60%	81%	70%	90%	74%	83%	87%	81%	90%	88%	72%	85%	81%	94%
83.2%	83%	90%	88%	83%	80%	80%	79%	86%	80%	84%	85%	79%	88%	78%	94%	83%	76%	80%	93%	83%	76%
81.0%	96%	75%	89%	93%	87%	67%	89%	91%	82%	85%	76%	87%	94%	78%	86%	89%	67%	76%	68%	69%	58%
90.5%	93%	99%	93%	93%	99%	10%	92%	95%	94%	83%	93%	94%	98%	99%	96%	100%	97%	97%	91%	92%	92%
72.7%	76%	69%	69%	77%	79%	60%	80%	76%	82%	86%	70%	66%	77%	68%	75%	85%	74%	60%	52%	65%	80%
72.0%	79%	72%	67%	69%	77%	65%	74%	73%	72%	75%	69%	77%	74%	73%	70%	73%	73%	63%	78%	65%	75%
58.8%	70%	72%	61%	61%	69%	46%	42%	34%	48%	70%	70%	62%	61%	61%	62%	68%	49%	64%	63%	49%	52%

Model Similarity Dendrogram

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