	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	3rd 78.9%	8th 77.2%	2nd 79.2%	1st 80.2%	10th 76.4%	14th 75.8%	6th 77.6%	15th 75.8%	12th 76.2%	5th 77.6%	4th 78.7%	20th 70.3%	9th 77.0%	13th 75.9%	16th 75.8%	7th 77.3%	19th 70.5%	21st 69.0%	11th 76.3%	18th 71.7%	17th 72.4%
79.3%	74%	73%	81%	81%	71%	74%	89%	79%	87%	87%	85%	81%	87%	85%	80%	75%	81%	62%	77%	77%	79%
72.4%	80%	74%	77%	79%	68%	80%	71%	65%	53%	76%	77%	74%	76%	77%	76%	76%	60%	60%	78%	66%	77%
70.5%	71%	65%	77%	77%	65%	73%	68%	68%	62%	77%	77%	71%	71%	68%	68%	68%	77%	70%	60%	74%	74%
77.4%	81%	72%	76%	78%	86%	71%	81%	81%	84%	71%	75%	77%	80%	79%	81%	83%	72%	78%	70%	79%	70%
87.0%	94%	83%	99%	99%	92%	92%	95%	90%	87%	86%	89%	80%	89%	87%	84%	93%	89%	61%	92%	68%	78%
86.6%	83%	88%	83%	83%	89%	88%	86%	95%	87%	87%	90%	90%	86%	87%	78%	86%	93%	93%	83%	81%	83%
76.2%	80%	79%	81%	85%	84%	67%	80%	88%	91%	71%	87%	56%	72%	69%	75%	84%	58%	91%	74%	53%	75%
78.5%	83%	84%	80%	76%	81%	60%	85%	76%	81%	83%	83%	76%	86%	80%	73%	83%	71%	72%	76%	87%	73%
68.1%	58%	67%	69%	64%	80%	78%	75%	72%	78%	69%	70%	75%	69%	68%	58%	58%	54%	70%	74%		55%
77.1%	81%	86%	75%	81%	86%	90%	75%	69%	76%	72%	75%	75%	76%	85%	72%	86%	65%	67%	81%	66%	81%
62.5%	76%	63%	72%	72%	54%	70%	53%	74%	62%	52%	68%	50%	52%	53%	67%	58%	68%	43%	80%	54%	72%
86.5%	78%	83%	91%	80%	85%	91%	93%	95%	88%	88%	90%	85%	88%	86%	85%	83%	81%	82%	91%	93%	80%
63.4%	70%	70%	75%	80%	62%	78%	66%	57%	62%	75%	73%	45%	67%	69%	76%	63%	71%	46%	76%	10%	41%
82.5%	88%	82%	85%	82%	82%	95%	81%	81%	87%	89%	84%	80%	88%	81%	84%	80%	80%	66%	75%	91%	71%
77.9%	79%	79%	77%	77%	76%	81%	74%	73%	78%	75%	81%	70%	82%	80%	79%	79%	80%	76%	82%	79%	79%
74.4%	75%	77%	79%	72%	68%	65%	79%	78%	76%	78%	79%	77%	78%	75%	73%	75%	67%	66%	77%	76%	72%
85.5%	91%	87%	86%	95%	95%	83%	80%	74%	84%	87%	87%	67%	85%	81%	91%	86%	84%	86%	89%	89%	88%
76.3%	83%	75%	79%	86%	94%	51%	67%	84%	70%	71%	63%	72%	77%	64%	86%	82%	81%	84%	72%	79%	82%
43.4%	49%	29%	51%	53%	60%	33%	46%	46%	46%	49%	52%	25%	43%	48%	49%	53%	34%	31%	29%	42%	43%
80.5%	79%	85%	85%	85%	81%	81%	85%	86%	81%	75%	87%	73%	79%	86%	77%	87%	59%	78%	92%	71%	79%
74.2%	82%	78%	81%	77%	76%	91%	81%	60%	76%	68%	82%	74%	81%	88%	62%	65%	62%	54%	92%	79%	50%
71.2%	73%	73%	75%	77%	62%	80%	76%	65%	73%	73%	79%	60%	72%	80%	63%	79%	68%	71%	74%	59%	64%
69.6%	58%	69%	63%	63%	87%	81%	68%	80%	69%	69%	80%	55%	80%	87%	66%	65%	69%	69%	66%	63%	55%
61.4%	68%	67%	74%	74%	60%	66%	45%	52%	57%	63%	63%	39%	59%	53%	79%	74%	69%	50%	73%	65%	40%
78.5%	83%	83%	83%	79%	76%	87%	83%	78%	74%	75%	86%	82%	84%	75%	80%	76%	70%	69%	81%	80%	64%
68.5%	63%	75%	79%	61%	72%	82%	72%	65%	68%	74%	78%	74%	71%	86%	65%	59%	55%	59%	78%	51%	51%
79.2%	83%	80%	86%	83%	89%	52%	84%	85%	80%	85%	74%	77%	77%	63%	79%	84%	81%	76%	78%	81%	86%
74.0%	79%	77%	76%	75%	69%	69%	78%	78%	69%	79%	78%	72%	77%	72%	70%	77%	74%	71%	67%	74%	72%
70.7%	86%	80%	84%	89%	82%	67%	74%	68%	67%	60%	76%	55%	61%	60%	74%	76%	63%	59%	68%	68%	67%
77.8%	82%	81%	79%	95%	82%	65%	79%	78%	78%	93%	85%	70%	81%	66%	85%	81%	43%	72%	80%	76%	82%
74.2%	79%	75%	76%	76%	70%	78%	69%	68%	73%	79%	77%	62%	73%	77%	83%	80%	65%	68%	76%	77%	77%
87.3%	88%	91%	82%	82%	94%	85%	91%	91%	97%	82%	82%	88%	88%	91%	82%	85%	86%	84%	100%	85%	79%
77.5%	85%	73%	82%	82%	70%	79%	73%	73%	67%	82%	82%	76%	76%	73%	79%	79%	78%	80%	65%	94%	79%
80.0%	94%	88%	78%	86%	73%	68%	87%	89%	90%	79%	81%	65%	74%	78%	83%	85%	55%	83%	72%	86%	87%
81.2%	83%	82%	87%	90%	43%	87%	78%	84%	85%	92%	82%	82%	88%	79%	82%	77%	89%	82%	77%	82%	74%
79.8%	90%	83%	89%	93%	65%	78%	87%	86%	76%	87%	82%	76%	84%	76%	68%	86%	73%	74%	68%	78%	76%
68.8%	69%	70%	74%	75%	64%	69%	74%	62%	66%	73%	68%	66%	69%	71%	73%	70%	68%	66%	65%	66%	67%
80.1%	91%	82%	97%	99%	83%	87%	96%	81%	88%	91%	88%	60%	85%	74%	80%	78%	61%	55%	80%	37%	89%
76.4%	86%	86%	82%	83%	72%	81%	77%	66%	74%	88%	75%	74%	80%	82%	76%	79%	62%	63%	66%	70%	83%
87.2%	79%	94%	82%	82%	94%	85%	91%	91%	97%	82%	82%	88%	88%	91%	82%	83%	81%	89%	100%	85%	85%
71.0%	72%	73%	72%	72%	82%	65%	75%	77%	78%	82%	72%	67%	72%	70%	78%	75%	67%	30%	63%	70%	80%
77.1%	79%	82%	70%	79%	76%	66%	76%	75%	70%	82%	83%	82%	75%	82%	80%	81%	78%	77%	79%	71%	76%
83.4%	86%	77%	77%	93%	87%	92%	93%	77%	85%	82%	76%	78%	87%	82%	78%	91%	88%	82%	84%	78%	78%

Model Similarity Dendrogram

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