	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	5th 77.4%	2nd 79.2%	4th 78.6%	3rd 78.7%	12th 75.3%	19th 71.5%	13th 74.7%	14th 74.6%	15th 73.7%	10th 76.0%	1st 79.7%	16th 73.2%	8th 76.6%	6th 77.2%	11th 75.6%	9th 76.1%	21st 69.8%	20th 69.9%	7th 76.7%	18th 72.3%	17th 72.9%
79.8%	82%	85%	80%	69%	85%	73%	83%	83%	83%	76%	83%	84%	85%	83%	78%	76%	68%	79%	90%	78%	73%
80.5%	76%	76%	76%	88%	73%	89%	79%	80%	61%	86%	86%	84%	82%	84%	84%	85%	72%	77%	83%	86%	84%
70.7%	67%	67%	75%	73%	55%	67%	67%	67%	63%	75%	71%	67%	71%	71%	80%	79%	63%	71%	63%	100%	73%
79.4%	85%	78%	77%	90%	80%	74%	74%	80%	75%	83%	77%	77%	74%	71%	76%	87%	82%	77%	71%	90%	90%
76.7%	72%	81%	69%	61%	77%	73%	65%	91%	78%	79%	86%	83%	86%	91%	70%	85%	85%	71%	72%	77%	59%
70.4%	65%	68%	65%	68%	71%	66%	72%	81%	77%	72%	72%	72%	72%	72%	57%	65%	72%	76%	72%	72%	72%
72.7%	77%	82%	74%	69%	75%	77%	73%	75%	69%	60%	82%	84%	73%	76%	63%	65%	64%	64%	88%		64%
81.6%	80%	85%	80%	80%	85%	60%	80%	85%	91%	69%	89%	84%	85%	84%	83%	84%	91%	57%	81%	93%	88%
86.1%	83%	95%	87%	94%	82%	61%	78%	90%	85%	87%	91%	80%	91%	86%	83%	82%	79%	90%	95%	95%	94%
85.0%	90%	86%	82%	90%	82%	82%	82%	88%	82%	90%	82%	87%	87%	84%	86%	85%	79%	82%	82%	93%	85%
61.1%	70%	74%	77%	69%	48%	71%	57%	57%	64%	46%	73%	57%	59%	53%	60%	57%	46%	35%	68%	66%	77%
77.4%	82%	81%	71%	83%	75%	78%	76%	71%	71%	85%	79%	77%	78%	71%	83%	75%	74%	75%	74%	85%	81%
80.0%	80%	85%	87%	75%	87%	85%	81%	67%	86%	86%	87%	64%	84%	87%	68%	86%	84%	48%	85%	87%	80%
62.6%	67%	66%	61%	61%	64%	71%	64%	69%	59%	62%	70%	58%	70%	65%	63%	61%	51%	60%	69%	48%	55%
81.8%	91%	83%	87%	82%	83%	68%	85%	76%	82%	84%	83%	81%	90%	83%	84%	78%	73%	79%	83%	85%	78%
69.6%	76%	71%	85%	77%	66%	55%	68%	68%	65%	70%	68%	71%	76%	68%	71%	67%	58%	67%	78%		67%
71.6%	77%	86%	86%	77%	65%	67%	67%	62%	68%	75%	75%	46%	65%	67%	77%	80%	59%	69%	75%	80%	80%
62.2%	71%	64%	70%	68%	63%	44%	58%	58%	65%	65%	60%	60%	68%	60%	67%	62%	61%	62%	64%	51%	66%
60.0%	68%	45%	72%	68%	74%	47%	62%	57%	60%	69%	80%	32%	63%	69%	66%	80%	49%	56%	42%	50%	52%
76.6%	82%	71%	83%	85%	73%	79%	79%	71%	64%	89%	77%	77%	83%	85%	81%	83%	70%	62%	79%		60%
74.3%	68%	79%	82%	77%	78%	89%	82%	67%	76%	73%	82%	76%	78%	86%	68%	63%	57%	68%	82%	61%	68%
83.3%	83%	91%	87%	89%	85%	80%	88%	71%	85%	88%	89%	71%	88%	89%	87%	88%	56%	89%	76%	83%	87%
53.3%	53%	50%	50%	55%	64%	64%	58%	62%	50%	50%	59%	38%	54%	71%	43%	52%	49%	51%	55%	46%	45%
70.9%	74%	77%	82%	87%	74%	68%	71%	68%	71%	78%	75%	60%	74%	71%	78%	73%	67%	61%	59%	53%	68%
68.6%	65%	90%	70%	65%	82%	75%	65%	71%	64%	55%	82%	76%	67%	72%	62%	66%	59%	66%	82%	53%	54%
68.1%	71%	78%	77%	71%	76%	69%	69%	66%	63%	74%	73%	81%	65%	76%	65%	70%	51%	62%	76%	47%	50%
76.2%	79%	85%	85%	87%	80%	59%	73%	78%	76%	76%	79%	77%	79%	79%	77%	80%	61%	68%	82%	72%	68%
84.6%	90%	90%	89%	89%	93%	69%	85%	85%	89%	86%	89%	85%	85%	77%	81%	90%	84%	89%	82%	55%	94%
58.7%	74%	80%	80%	85%	62%	58%	53%	54%	52%	49%	62%	38%	44%	50%	69%	61%	45%	45%	66%	49%	57%
72.0%	75%	74%	81%	78%	81%	53%	67%	75%	78%	73%	72%	60%	71%	66%	84%	74%	74%	72%	71%	69%	65%
83.3%	89%	85%	86%	86%	77%	73%	83%	75%	84%	89%	94%	78%	84%	88%	82%	90%	86%	73%	89%	77%	82%
67.6%	70%	70%	61%	63%	83%	70%	70%	70%	74%	61%	66%	70%	66%	66%	61%	70%	74%	66%	74%	51%	63%
94.6%	95%	95%	95%	98%	83%	95%	95%	95%	91%	95%	100%	95%	100%	100%	98%	95%	91%	83%	91%	98%	98%
73.6%	70%	74%	79%	70%	66%	75%	82%	75%	70%	82%	71%	71%	82%	71%	75%	74%	69%	62%	71%	79%	77%
78.7%	81%	85%	81%	81%	79%	80%	79%	81%	79%	81%	82%	79%	79%	88%	81%	82%	72%	81%	72%	61%	68%
79.3%	81%	81%	85%	87%	57%	80%	90%	90%	76%	78%	93%	86%	81%	85%	71%	64%	86%	75%	84%	60%	75%
78.6%	83%	82%	83%	91%	70%	71%	83%	77%	80%	86%	79%	82%	73%	73%	87%	80%	72%	74%	78%		67%
85.0%	81%	92%	87%	87%	95%	88%	77%	95%	87%	91%	95%	95%	77%	95%	88%	86%	73%	52%	88%	76%	81%
68.8%	67%	72%	71%	76%	70%	61%	73%	68%	65%	76%	73%	70%	73%	65%	74%	68%	59%	70%	60%	62%	72%
92.9%	96%	96%	86%	89%	91%	96%	96%	96%	100%	86%	91%	96%	91%	91%	91%	83%	100%	91%	100%	96%	89%
73.3%	76%	73%	74%	73%	70%	72%	77%	74%	66%	76%	77%	75%	73%	75%	75%	70%	75%	73%	71%	73%	71%
74.8%	75%	84%	75%	80%	66%	52%	70%	70%	66%	75%	82%	71%	80%	86%	80%	75%		83%	80%	69%	76%
88.5%	91%	92%	91%	91%	91%	91%	77%	69%	77%	83%	93%	93%	86%	91%	93%	95%	91%	94%	93%	95%	81%

Model Similarity Dendrogram

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