	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	3rd 78.6%	5th 77.2%	1st 79.9%	17th 72.6%	15th 73.2%	18th 71.6%	8th 75.3%	9th 74.9%	13th 74.3%	6th 77.1%	7th 76.0%	16th 73.0%	10th 74.8%	14th 74.0%	2nd 79.2%	4th 77.2%	19th 71.0%	20th 70.3%	10th 74.8%	12th 74.6%	21st 69.9%
75.7%	74%	69%	84%	76%	73%	67%	84%	77%	79%	73%	78%	77%	78%	83%	80%	66%	78%	61%	77%	78%	77%
70.9%	67%	71%	72%	69%	67%	69%	70%	65%	75%	71%	71%	70%	74%	76%	72%	75%	67%	70%	73%	77%	67%
65.9%	70%	64%	78%	0%	58%	70%	68%	68%	58%	77%	78%	77%	71%	74%	68%	72%	65%	74%	60%	75%	58%
89.6%	86%	90%	89%	94%	86%	90%	89%	83%	84%	92%	89%	95%	86%	88%	92%	92%	94%	91%	90%	93%	88%
89.1%	89%	89%	91%	89%	90%	94%	93%	94%	88%	93%	89%	89%	90%	85%	88%	84%	94%	85%	88%	94%	76%
84.3%	95%	92%	93%	93%	85%	84%	84%	76%	80%	87%	83%	90%	81%	81%	86%	88%	90%	88%	78%	74%	62%
82.8%	86%	80%	84%	85%	79%	82%	80%	88%	88%	79%	84%	79%	80%	82%	88%	89%	80%	81%	80%	87%	78%
78.3%	82%	81%	82%	84%	71%	56%	73%	88%	76%	77%	77%	80%	77%	68%	88%	82%	87%	85%	67%	86%	77%
81.3%	89%	88%	91%	92%	70%	64%	81%	79%	73%	85%	88%	87%	78%	88%	88%	83%	79%	74%	84%	88%	58%
93.3%	94%	81%	96%	97%	95%	95%	92%	89%	95%	95%	95%	95%	95%	95%	100%	92%	92%	78%	95%	98%	96%
78.0%	89%	81%	92%	89%	62%	92%	92%	92%	87%	69%	73%	93%	65%	68%	74%	64%	62%	44%	94%	87%	70%
80.1%	96%	78%	81%	86%	86%	86%	84%	86%	85%	72%	69%	86%	54%	74%	87%	80%	64%	78%	86%	78%	86%
74.1%	68%	74%	74%	77%	75%	76%	70%	71%	70%	73%	75%	74%	74%	73%	76%	80%	76%	74%	78%	74%	74%
70.7%	75%	74%	76%	73%	70%	65%	80%	71%	77%	71%	80%	58%	74%	61%	80%	68%	55%	65%	73%	76%	62%
71.7%	77%	73%	73%	76%	73%	72%	71%	59%	62%	69%	75%	55%	75%	74%	75%	70%	76%	71%	73%	79%	77%
78.3%	81%	82%	83%	80%	77%	65%	79%	86%	80%	80%	79%	79%	80%	76%	80%	78%	76%	77%	76%	79%	71%
57.8%	66%	65%	79%	64%	54%	46%	60%	46%	60%	57%	61%	42%	48%	51%	64%	65%	49%	51%	60%	55%	70%
68.8%	80%	74%	76%	80%	73%	45%	62%	69%	65%	72%	58%	65%	68%	58%	77%	76%	76%	74%	59%	67%	70%
57.3%	55%	48%	52%	47%	89%	33%	54%	62%	62%	70%	45%	31%	70%	65%	96%	90%	45%	43%	37%	46%	64%
69.9%	75%	80%	76%	75%	72%	59%	73%	69%	63%	76%	64%	60%	72%	58%	78%	76%	63%	76%	68%	60%	74%
77.5%	78%	83%	86%	84%	80%	80%	84%	87%	80%	83%	84%	78%	78%	78%	78%	78%	60%	58%	70%	84%	57%
69.5%	70%	72%	73%	71%	63%	74%	68%	65%	72%	77%	74%	73%	80%	75%	68%	74%	58%	62%	70%	77%	43%
75.4%	79%	76%	70%	81%	79%	83%	78%	81%	75%	84%	67%	76%	59%	76%	74%	70%	73%	77%	79%	77%	69%
78.7%	84%	86%	86%	83%	73%	75%	85%	73%	83%	87%	83%	63%	73%	84%	78%	84%	73%	75%	78%	73%	73%
68.0%	70%	70%	74%	74%	78%	66%	77%	67%	79%	71%	81%	53%	75%	58%	71%	66%	46%	68%	71%	67%	46%
66.2%	68%	71%	66%	64%	71%	69%	62%	66%	70%	74%	67%	61%	64%	73%	66%	71%	71%	49%	75%	66%	46%
72.8%	76%	79%	82%	81%	75%	51%	72%	78%	72%	76%	60%	72%	77%	69%	74%	73%	73%	76%	76%	71%	66%
79.2%	90%	86%	82%	82%	77%	67%	81%	86%	89%	84%	74%	78%	81%	65%	90%	91%	73%	70%	68%	69%	80%
75.3%	78%	85%	85%	95%	76%	62%	78%	75%	78%	69%	68%	76%	64%	68%	78%	78%	68%	65%	80%	76%	80%
71.8%	73%	75%	71%	82%	87%	62%	57%	78%	70%	75%	77%	69%	76%	64%	78%	75%	78%	27%	78%	87%	69%
56.8%	63%	53%	55%	60%	54%	62%	46%	49%	51%	56%	64%	43%	56%	59%	58%	63%	54%	54%	67%	63%	63%
61.9%	64%	70%	56%	0%	77%	64%	66%	66%	77%	57%	56%	57%	63%	60%	66%	62%	69%	60%	74%	59%	77%
74.7%	79%	73%	88%	0%	66%	79%	77%	77%	66%	86%	88%	86%	80%	83%	77%	81%	74%	83%	69%	90%	66%
69.1%	77%	66%	72%	74%	83%	66%	63%	73%	71%	77%	65%	60%	69%	65%	75%	68%	66%	67%	58%	67%	69%
82.9%	85%	88%	85%	86%	79%	86%	77%	77%	81%	89%	84%	84%	84%	75%	87%	85%	86%	70%	77%	84%	92%
73.5%	71%	80%	77%	77%	54%	82%	72%	73%	76%	68%	77%	83%	72%	81%	72%	63%	67%	76%	81%	78%	64%
77.3%	86%	80%	85%	87%	77%	81%	67%	63%	69%	81%	86%	61%	74%	76%	87%	79%	79%	79%	80%	69%	78%
82.0%	83%	91%	95%	95%	76%	89%	90%	91%	88%	95%	81%	72%	95%	85%	90%	93%	68%	73%	85%	43%	43%
73.1%	79%	77%	80%	81%	72%	80%	77%	71%	71%	77%	76%	67%	74%	67%	75%	76%	71%	67%	64%	66%	67%
84.3%	94%	84%	99%	0%	77%	90%	88%	88%	77%	97%	99%	97%	91%	94%	88%	92%	85%	94%	80%	79%	77%
81.8%	94%	91%	90%	91%	43%	85%	90%	93%	70%	81%	90%	83%	91%	92%	85%	83%	48%	79%	89%	76%	74%
75.8%	76%	78%	76%	79%	74%	50%	80%	75%	65%	67%	82%	83%	79%	83%	83%	81%	77%	79%	83%	72%	69%
68.6%	70%	70%	80%	70%	53%	67%	65%	49%	58%	68%	76%	81%	70%	74%	69%	65%	66%	77%	67%	65%	81%

Model Similarity Dendrogram

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