	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	7th 75.1%	1st 75.8%	3rd 75.7%	5th 75.5%	14th 71.4%	15th 70.6%	9th 74.5%	12th 72.6%	13th 72.1%	4th 75.5%	8th 74.8%	16th 70.6%	2nd 75.8%	11th 74.1%	10th 74.3%	6th 75.1%	17th 70.3%	21st 64.4%	18th 70.2%	19th 69.2%	20th 69.1%
78.1%	71%	79%	75%	78%	74%	58%	79%	84%	79%	92%	79%	75%	75%	82%	87%	83%	62%	84%	76%		90%
66.3%	64%	57%	72%	71%	65%	72%	64%	58%	45%	82%	65%	77%	71%	72%	78%	79%	78%	56%	64%	45%	58%
60.6%	61%	53%	55%	61%	55%	58%	51%	61%	51%	61%	81%	67%	56%	55%	56%	57%	74%	50%	47%	81%	81%
87.0%	80%	88%	80%	80%	90%	82%	100%	90%	90%	94%	80%	81%	100%	100%	89%	90%	88%	81%	72%	81%	90%
75.2%	81%	74%	86%	89%	80%	83%	86%	80%	80%	64%	70%	70%	70%	71%	74%	64%	69%	62%	81%	72%	73%
90.9%	96%	96%	90%	96%	99%	92%	88%	95%	92%	95%	95%	95%	95%	83%	80%	95%	95%	89%	95%	82%	65%
75.8%	84%	85%	86%	67%	60%	63%	84%	80%	85%	63%	80%	86%	74%	89%	76%	84%	59%	78%	92%	58%	59%
71.2%	73%	78%	74%	77%	73%	59%	77%	74%	71%	89%	77%	69%	77%	71%	65%	68%	55%	52%	68%	74%	74%
73.1%	81%	75%	60%	71%	70%	49%	60%	65%	65%	86%	86%	63%	79%	78%	81%	81%	93%	63%	65%	79%	85%
71.5%	81%	76%	67%	67%	73%	76%	73%	64%	60%	73%	78%	81%	81%	63%	81%	75%	58%	62%	68%	68%	76%
77.1%	84%	84%	87%	87%	69%	78%	75%	74%	78%	68%	90%	76%	82%	74%	67%	79%	89%	54%	76%	86%	63%
69.8%	65%	71%	73%	70%	75%	74%	69%	63%	73%	67%	73%	75%	67%	73%	75%	67%	66%	76%	71%	71%	52%
76.3%	79%	83%	80%	78%	78%	85%	77%	70%	71%	83%	84%	58%	76%	77%	84%	82%	63%	63%	76%	79%
80.7%	81%	88%	84%	87%	65%	68%	89%	88%	88%	67%	87%	87%	87%	88%	83%	84%	77%	78%	94%	57%	67%
73.8%	81%	76%	76%	77%	74%	78%	69%	61%	69%	83%	77%	62%	77%	73%	82%	76%	76%	66%	73%	74%	70%
68.8%	74%	71%	67%	72%	68%	49%	71%	72%	70%	67%	66%	70%	72%	67%	72%	66%	75%	71%	70%	64%	70%
62.3%	73%	70%	75%	73%	61%	54%	61%	51%	60%	57%	71%	55%	60%	57%	64%	66%	57%	32%	61%	77%	74%
77.4%	72%	78%	75%	74%	69%	63%	81%	84%	81%	96%	80%	81%	78%	83%	83%	79%	75%	61%	79%	67%	86%
40.0%	49%	38%	44%	43%	54%	33%	48%	48%	40%	37%	37%	34%	37%	29%	40%	56%	37%	33%	27%	41%	35%
83.0%	89%	74%	92%	85%	87%	86%	100%	73%	79%	76%	91%	75%	80%	88%	79%	81%	82%	85%	83%	74%	85%
65.5%	70%	71%	69%	64%	66%	66%	70%	63%	71%	77%	71%	71%	70%	71%	58%	71%	46%	42%	56%	71%	61%
80.9%	91%	91%	90%	77%	91%	69%	90%	84%	91%	79%	81%	83%	89%	81%	92%	74%	81%	82%	53%	70%	60%
68.6%	63%	76%	65%	65%	84%	87%	65%	78%	65%	65%	65%	53%	73%	77%	65%	70%	73%	53%	65%		65%
70.5%	71%	78%	89%	81%	73%	75%	68%	67%	67%	82%	82%	45%	74%	62%	75%	79%	74%	57%	67%	76%	38%
73.6%	76%	74%	73%	73%	73%	70%	76%	77%	78%	77%	63%	73%	71%	77%	76%	78%	77%	77%	72%	58%	77%
65.8%	61%	71%	74%	75%	71%	72%	70%	59%	61%	71%	75%	70%	70%	74%	49%	67%	54%	64%	67%	53%	54%
64.7%	64%	66%	72%	77%	68%	53%	62%	66%	63%	71%	66%	63%	64%	68%	60%	68%	64%	56%	64%	63%	60%
65.7%	65%	69%	65%	73%	73%	48%	71%	73%	62%	69%	67%	58%	63%	58%	69%	70%	60%	60%	59%	75%	73%
64.8%	80%	73%	73%	73%	73%	58%	73%	57%	59%	59%	65%	57%	65%	59%	72%	65%	54%	57%	65%	59%	65%
75.5%	69%	81%	69%	70%	65%	67%	71%	78%	83%	71%	68%	74%	81%	86%	78%	80%	80%	72%	75%	71%	96%
61.9%	65%	64%	70%	72%	63%	69%	62%	55%	63%	72%	61%	56%	60%	58%	65%	60%	61%	51%	58%	54%	61%
87.0%	93%	83%	86%	93%	86%	89%	81%	93%	81%	93%	83%	100%	87%	86%	87%	88%	92%	80%	76%	83%	87%
91.3%	91%	99%	99%	92%	99%	95%	97%	91%	97%	91%	68%	84%	97%	99%	97%	97%	91%	95%	91%	68%	80%
82.9%	87%	89%	78%	72%	72%	82%	87%	88%	93%	74%	88%	66%	92%	94%	93%	85%	84%	77%	86%	79%	75%
78.8%	75%	86%	87%	90%	32%	77%	79%	90%	90%	90%	87%	92%	86%	72%	66%	72%	83%	72%	64%	73%	92%
66.7%	69%	69%	63%	59%	47%	79%	66%	70%	53%	69%	72%	69%	81%	69%	65%	68%	63%	63%	74%	78%	54%
59.1%	62%	60%	64%	66%	55%	66%	59%	52%	56%	66%	62%	54%	62%	58%	56%	63%	57%	44%	53%	66%	61%
73.3%	83%	76%	88%	88%	92%	76%	88%	76%	88%	76%	85%	64%	83%	75%	69%	81%	41%	29%	71%	56%	55%
66.7%	61%	72%	71%	69%	61%	60%	69%	76%	69%	73%	69%	69%	72%	69%	74%	71%	55%	70%	66%	71%	34%
91.4%	97%	93%	95%	98%	95%	99%	91%	97%	91%	97%	74%	90%	97%	95%	97%	98%	83%	90%	85%	74%	83%
65.1%	71%	68%	72%	66%	50%	83%	68%	64%	47%	71%	66%	72%	69%	67%	73%	67%	71%	31%	67%	64%	61%
78.3%	79%	84%	79%	79%	76%	69%	75%	77%	80%	83%	77%	71%	87%	80%	83%	79%	77%	79%	79%	75%	77%
70.1%	66%	73%	68%	73%	66%	67%	64%	57%	64%	72%	73%	65%	73%	77%	81%	67%	72%	73%	69%	72%	81%

Model Similarity Dendrogram

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