	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 81.4%	3rd 79.8%	6th 78.0%	2nd 80.0%	5th 78.9%	21st 70.6%	12th 75.9%	9th 77.6%	13th 75.9%	8th 77.7%	7th 78.0%	20th 71.9%	10th 76.8%	15th 74.7%	11th 76.4%	4th 79.1%	14th 74.7%	18th 73.0%	19th 72.7%	17th 73.3%	16th 73.3%
83.3%	93%	80%	83%	91%	88%	71%	80%	80%	83%	87%	85%	82%	83%	87%	91%	85%	85%	75%	74%	86%	81%
75.4%	82%	74%	80%	89%	60%	76%	68%	82%	54%	76%	78%	79%	74%	83%	85%	80%	81%	71%	79%	60%	72%
66.4%	67%	64%	67%	65%	69%	78%	64%	76%	68%	74%	69%	66%	68%	64%	62%	65%	61%	54%	64%	62%	67%
50.6%	54%	57%	48%	38%	49%	51%	62%	50%	49%	49%	59%	24%	58%	68%	50%	46%	45%	35%	58%	59%	53%
89.8%	90%	90%	94%	90%	90%	82%	85%	80%	88%	89%	97%	92%	99%	94%	92%	85%	95%	90%	89%	95%	80%
84.6%	90%	93%	89%	89%	93%	68%	84%	88%	88%	85%	83%	70%	84%	82%	82%	86%	81%	88%	85%	86%	82%
86.1%	91%	87%	93%	92%	90%	86%	83%	85%	85%	91%	87%	90%	82%	76%	91%	90%	87%	74%	79%	82%	88%
75.3%	84%	73%	72%	71%	91%	63%	70%	70%	77%	84%	65%	88%	76%	68%	88%	86%	73%	82%	64%	65%	72%
85.0%	85%	87%	85%	86%	92%	73%	84%	89%	85%	89%	85%	89%	86%	82%	74%	86%	92%	84%	81%	87%	83%
53.9%	64%	65%	47%	56%	54%	53%	61%	54%	49%	41%	61%	36%	53%	56%	60%	54%	56%	64%	67%	51%	29%
86.0%	88%	88%	84%	84%	94%	72%	89%	83%	90%	91%	90%	85%	85%	89%	91%	88%	87%	80%	88%	84%	77%
53.9%	67%	71%	48%	62%	60%	44%	53%	56%	53%	48%	56%	27%	53%	60%	59%	64%	53%	51%	55%	49%	43%
84.9%	83%	91%	90%	92%	90%	87%	81%	83%	85%	90%	83%	72%	91%	83%	89%	83%	81%	81%	76%	84%	88%
82.0%	86%	87%	89%	75%	88%	82%	82%	91%	79%	77%	81%	75%	81%	91%	73%	79%	84%	80%	74%	82%	85%
83.7%	91%	93%	90%	98%	83%	79%	93%	86%	90%	83%	87%	81%	90%	78%	88%	81%	75%	81%	74%	67%	69%
80.4%	94%	80%	82%	91%	88%	65%	79%	82%	80%	80%	81%	77%	72%	75%	89%	88%	80%	67%	67%	85%	87%
66.6%	65%	81%	67%	69%	71%	69%	65%	68%	66%	66%	68%	65%	62%	56%	75%	75%	66%	56%	65%	58%	65%
67.7%	78%	68%	72%	75%	78%	49%	60%	70%	65%	64%	67%	69%	61%	59%	72%	69%	70%	59%	66%	72%	79%
72.7%	68%	69%	69%	78%	66%	50%	89%	73%	71%	83%	71%	66%	80%	66%	83%	84%	85%	65%	68%	77%	65%
80.5%	88%	82%	85%	85%	83%	89%	82%	79%	76%	80%	77%	74%	85%	83%	78%	81%	72%	75%	76%	80%	81%
85.0%	85%	93%	94%	95%	82%	66%	90%	89%	89%	89%	92%	92%	87%	74%	93%	90%	74%	74%	68%		84%
82.0%	88%	81%	81%	86%	86%	72%	85%	85%	83%	81%	87%	83%	84%	82%	87%	87%	80%	77%	69%	74%	85%
78.5%	95%	81%	85%	85%	75%	61%	78%	81%	77%	85%	82%	51%	73%	77%	88%	87%	70%	79%	82%	83%	73%
83.2%	94%	92%	92%	94%	80%	92%	86%	90%	94%	93%	87%	68%	95%	95%	0%	92%	83%	76%	79%	82%	84%
82.1%	83%	87%	90%	78%	86%	83%	87%	85%	82%	77%	85%	78%	85%	85%	74%	79%	80%	73%	81%	86%	80%
74.6%	76%	72%	74%	77%	76%	70%	66%	68%	76%	74%	79%	76%	75%	78%	71%	75%	76%	74%	76%	76%	81%
65.0%	79%	68%	70%	70%	67%	50%	60%	68%	63%	69%	58%	66%	64%	57%	77%	67%	57%	62%	58%	69%	67%
74.3%	81%	75%	70%	74%	95%	55%	71%	85%	81%	82%	72%	71%	74%	53%	89%	79%	73%	73%	65%	61%	81%
55.0%	54%	68%	56%	68%	65%	45%	48%	71%	47%	48%	66%	24%	48%	53%	51%	65%	59%	59%	56%	62%	42%
71.3%	78%	77%	70%	77%	80%	68%	55%	60%	69%	68%	76%	72%	64%	69%	73%	77%	81%	85%	67%	64%	68%
84.6%	91%	87%	77%	95%	85%	79%	88%	84%	86%	89%	87%	85%	82%	73%	91%	90%	88%	83%	74%	74%	89%
80.1%	82%	82%	80%	81%	77%	68%	82%	70%	78%	72%	77%	80%	78%	83%	79%	81%	86%	89%	82%	89%	86%
61.8%	60%	60%	62%	61%	64%	73%	60%	71%	63%	70%	64%	62%	64%	59%	58%	64%	56%	56%	60%	54%	56%
76.3%	78%	75%	79%	73%	79%	83%	78%	80%	75%	78%	73%	80%	80%	76%	72%	74%	79%	75%	66%	75%	74%
69.9%	83%	80%	71%	71%	61%	64%	63%	66%	66%	70%	65%	64%	83%	84%	66%	74%	64%	72%	84%	66%	51%
84.0%	93%	93%	90%	88%	71%	86%	93%	92%	72%	87%	86%	87%	84%	83%	72%	86%	86%	79%	80%	72%	83%
81.3%	84%	85%	84%	84%	84%	78%	80%	83%	83%	86%	92%	90%	79%	72%	76%	84%	70%	89%	80%	77%	68%
85.6%	90%	93%	86%	86%	86%	86%	86%	84%	89%	86%	91%	75%	85%	84%	88%	91%	74%		94%	74%	85%
72.5%	88%	76%	76%	82%	80%	63%	76%	79%	71%	83%	73%	74%	73%	62%	79%	78%	72%	59%	59%	66%	53%
95.5%	95%	96%	98%	97%	99%	89%	96%	92%	100%	93%	99%	98%	100%	95%	95%	99%	92%	98%	96%	85%	94%
78.8%	79%	73%	87%	86%	88%	69%	86%	82%	90%	87%	80%	68%	82%	73%	83%	80%	60%	72%	63%	84%	83%
73.3%	73%	77%	70%	75%	70%	72%	72%	79%	75%	75%	73%	75%	76%	76%	76%	74%	71%	75%	67%	67%	71%
72.7%	82%	79%	78%	79%	78%	77%	64%	66%	73%	70%	78%	66%	66%	67%	77%	75%	71%	77%	69%	66%	69%

Model Similarity Dendrogram

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