	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 82.3%	2nd 82.3%	1st 82.4%	4th 82.0%	5th 80.8%	21st 65.3%	7th 79.2%	13th 78.1%	12th 78.2%	10th 78.6%	11th 78.5%	15th 76.9%	9th 78.7%	14th 77.2%	8th 78.9%	6th 80.6%	16th 75.7%	18th 75.1%	17th 75.5%	19th 74.8%	20th 72.5%
79.2%	94%	85%	81%	91%	76%	62%	76%	74%	75%	74%	80%	79%	85%	77%	80%	84%	86%	73%	79%	80%	72%
75.3%	73%	70%	79%	79%	60%	92%	59%	76%	50%	78%	82%	84%	72%	82%	88%	79%	71%	74%	86%	76%	71%
65.6%	73%	61%	75%	72%	66%	10%	64%	75%	65%	81%	69%	66%	70%	66%	66%	69%	70%	70%	61%	67%	62%
86.5%	89%	86%	88%	88%	89%	85%	88%	89%	88%	88%	86%	90%	89%	82%	87%	84%	87%	82%	85%	77%	89%
87.9%	86%	96%	85%	86%	92%	82%	81%	91%	88%	97%	94%	94%	97%	90%	92%	93%	95%	75%	76%	81%	75%
88.5%	93%	93%	95%	95%	96%	89%	90%	87%	88%	88%	90%	69%	85%	78%	84%	88%	87%	96%	95%	77%	95%
78.7%	86%	86%	89%	89%	86%	68%	88%	85%	84%	69%	80%	78%	70%	85%	73%	78%	69%	81%	78%	64%	66%
77.5%	81%	78%	72%	86%	76%	42%	77%	92%	89%	79%	74%	79%	78%	69%	97%	90%	72%	85%	67%	72%	73%
84.9%	75%	87%	87%	82%	92%	69%	83%	90%	89%	89%	87%	93%	86%	86%	75%	87%	87%	92%	81%	97%	69%
89.0%	94%	95%	90%	91%	87%	92%	91%	80%	88%	94%	93%	90%	86%	87%	91%	90%	83%	85%	90%	84%	87%
81.8%	88%	85%	84%	84%	86%	84%	89%	75%	88%	81%	88%	87%	80%	81%	85%	84%	80%	63%	74%	81%	70%
88.2%	86%	89%	92%	88%	89%	93%	89%	80%	91%	92%	87%	94%	87%	87%	91%	90%	75%	87%	89%	86%	90%
85.4%	85%	90%	91%	92%	89%	78%	85%	91%	87%	90%	86%	74%	90%	89%	90%	90%	83%	72%	74%	82%	85%
77.6%	82%	86%	86%	80%	80%	77%	85%	74%	79%	70%	83%	71%	75%	92%	78%	73%	70%	73%	91%	62%	63%
85.3%	88%	91%	92%	95%	90%	71%	89%	90%	88%	81%	85%	86%	85%	84%	95%	85%	87%	84%	70%	82%	73%
75.7%	89%	88%	94%	91%	87%	57%	70%	62%	71%	78%	73%	74%	82%	71%	82%	87%	65%	58%	76%	63%	71%
66.0%	78%	85%	88%	72%	65%	63%	64%	54%	62%	66%	62%	61%	65%	58%	74%	67%	45%	67%	72%	64%	53%
67.0%	85%	66%	73%	86%	76%	49%	59%	57%	56%	66%	62%	63%	67%	56%	72%	68%	68%	80%	68%	71%	60%
50.8%	55%	40%	62%	52%	72%	41%	55%	47%	51%	51%	53%	42%	52%	47%	58%	74%	45%	35%	38%	53%	44%
82.8%	90%	93%	88%	84%	83%	86%	90%	75%	75%	82%	85%	75%	87%	90%	82%	82%	74%	88%	84%	72%	73%
83.5%	90%	97%	93%	87%	61%	64%	94%	85%	89%	84%	85%	92%	84%	84%	80%	95%	91%	85%	66%	78%	69%
80.8%	84%	80%	76%	82%	85%	72%	85%	78%	82%	81%	79%	85%	83%	81%	83%	87%	81%	84%	69%	77%	82%
74.3%	69%	67%	67%	67%	94%	85%	88%	84%	69%	75%	70%	63%	75%	89%	73%	69%	76%	68%	67%	71%	74%
85.0%	85%	91%	91%	82%	82%	87%	86%	87%	91%	87%	87%	77%	91%	88%	93%	90%	88%	80%	82%	82%	58%
80.1%	81%	85%	84%	73%	84%	78%	85%	77%	81%	66%	86%	84%	81%	89%	67%	80%	87%	83%	91%	77%	64%
69.1%	70%	73%	74%	67%	80%	65%	67%	58%	73%	65%	72%	72%	66%	72%	61%	69%	65%	73%	74%	70%	65%
63.7%	81%	64%	71%	82%	74%	43%	55%	60%	64%	58%	49%	61%	64%	56%	75%	67%	73%	58%	61%	67%	55%
77.0%	87%	89%	81%	80%	90%	47%	82%	85%	82%	83%	69%	82%	74%	61%	89%	84%	65%	84%	65%	53%	86%
71.6%	86%	90%	82%	81%	78%	69%	73%	65%	67%	67%	69%	63%	65%	65%	72%	71%	69%	63%	66%	69%	73%
78.0%	88%	89%	88%	93%	87%	66%	65%	87%	77%	75%	76%	57%	71%	76%	84%	78%	81%	76%	87%	68%	68%
79.0%	89%	87%	85%	88%	85%	68%	84%	83%	87%	81%	83%	90%	81%	76%	0%	91%	82%	83%	68%	75%	92%
75.0%	74%	86%	71%	74%	80%	10%	83%	71%	81%	65%	77%	80%	76%	80%	85%	75%	76%	76%	86%	85%	84%
59.6%	62%	56%	70%	68%	62%	10%	59%	70%	61%	76%	64%	62%	66%	62%	61%	56%	56%	58%	56%	58%	58%
79.8%	77%	83%	79%	73%	70%	83%	89%	87%	79%	75%	80%	80%	94%	76%	87%	80%	82%	70%	78%	80%	73%
78.5%	76%	71%	85%	83%	90%	83%	80%	85%	76%	87%	82%	76%	83%	94%	71%	74%	73%	78%	60%	78%	63%
85.8%	93%	93%	99%	92%	69%	67%	94%	94%	85%	89%	85%	82%	90%	79%	82%	84%	90%	81%	80%	83%	90%
80.0%	78%	88%	79%	81%	89%	66%	80%	81%	90%	82%	78%	89%	80%	80%	81%	83%	82%	67%	81%	75%	69%
86.2%	94%	93%	92%	91%	83%	86%	85%	95%	85%	92%	86%	74%	89%	73%	95%	95%	70%	66%	98%	87%	82%
73.4%	88%	81%	78%	79%	64%	57%	77%	90%	72%	79%	73%	73%	71%	66%	84%	81%	66%	62%	65%	78%	57%
90.9%	94%	92%	92%	95%	98%	10%	95%	92%	97%	87%	99%	98%	98%	98%	96%	99%	92%	98%	92%	94%	93%
80.1%	83%	80%	77%	80%	92%	71%	86%	82%	89%	85%	80%	64%	73%	72%	88%	72%	77%	77%	79%	88%	88%
74.6%	74%	78%	74%	77%	73%	71%	75%	74%	75%	79%	72%	83%	77%	77%	79%	74%	77%	58%	74%	71%	75%
65.7%	64%	78%	63%	67%	67%	61%	65%	43%	60%	68%	77%	70%	65%	68%	68%	68%	59%	80%	68%	60%	60%

Model Similarity Dendrogram

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