	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 83.3%	5th 82.5%	9th 81.4%	4th 82.7%	7th 81.9%	19th 76.4%	10th 81.1%	11th 81.0%	14th 78.8%	8th 81.6%	12th 80.6%	20th 76.0%	6th 82.3%	16th 78.0%	3rd 82.9%	2nd 83.3%	13th 79.5%	18th 76.9%	17th 77.5%	21st 75.3%	15th 78.4%
82.3%	88%	88%	78%	85%	81%	62%	85%	89%	83%	84%	82%	85%	86%	78%	87%	86%	78%	89%	72%	82%	81%
88.9%	88%	90%	93%	93%	90%	95%	95%	92%	83%	92%	89%	80%	90%	91%	90%	94%	82%	85%	89%	87%	79%
68.0%	64%	67%	70%	70%	64%	75%	66%	70%	67%	70%	75%	68%	70%	70%	65%	70%	67%	67%	62%	68%	64%
69.4%	65%	74%	65%	59%	74%	72%	75%	59%	62%	66%	73%	59%	74%	75%	63%	67%	73%	74%	87%	68%	73%
91.7%	92%	98%	90%	90%	89%	93%	90%	87%	87%	89%	96%	94%	95%	96%	94%	89%	88%	91%	96%	93%	88%
80.0%	80%	89%	82%	87%	83%	75%	84%	80%	77%	78%	75%	91%	77%	74%	81%	87%	86%	83%	73%	70%	69%
84.5%	84%	73%	80%	86%	88%	81%	81%	92%	86%	90%	87%	89%	85%	74%	83%	93%	91%	81%	78%	87%	86%
76.6%	77%	67%	78%	77%	70%	67%	75%	74%	80%	85%	81%	81%	81%	80%	89%	85%	81%	73%	64%	84%	59%
87.3%	88%	88%	81%	80%	88%	87%	78%	87%	84%	93%	88%	92%	89%	91%	82%	95%	93%	75%	88%	99%	88%
66.2%	68%	69%	58%	59%	76%	68%	68%	55%	69%	60%	67%	38%	70%	71%	56%	65%	72%	85%	86%	66%	64%
84.0%	91%	92%	92%	90%	82%	92%	90%	92%	78%	81%	91%	74%	89%	68%	80%	89%	73%	59%	92%	80%	90%
65.1%	66%	85%	53%	60%	77%	69%	68%	56%	51%	56%	70%	50%	62%	61%	63%	62%	73%	73%	85%	53%	74%
89.6%	88%	95%	97%	97%	91%	88%	91%	93%	87%	95%	85%	68%	88%	86%	98%	95%	86%	90%	84%	90%	90%
89.8%	94%	89%	92%	85%	93%	87%	84%	93%	88%	90%	92%	86%	97%	86%	93%	88%	90%	85%	87%	91%	95%
86.4%	92%	92%	95%	96%	83%	81%	89%	88%	82%	92%	87%	79%	88%	86%	89%	88%	85%	76%	82%	87%	78%
81.4%	84%	82%	80%	93%	79%	68%	84%	92%	79%	86%	83%	80%	81%	74%	84%	85%	81%	77%	69%	81%	87%
70.0%	77%	73%	73%	78%	69%	79%	70%	57%	66%	66%	61%	71%	61%	56%	80%	76%	72%	78%	71%	66%	71%
67.1%	69%	67%	67%	76%	66%	49%	63%	70%	64%	68%	71%	68%	69%	58%	73%	69%	68%	67%	58%	78%	72%
70.4%	82%	64%	79%	79%	65%	57%	84%	62%	69%	79%	70%	70%	83%	74%	79%	81%	62%	55%	58%	55%	71%
82.4%	86%	78%	80%	91%	86%	95%	81%	95%	89%	84%	87%	92%	88%	77%	83%	91%	93%	84%	81%	10%	79%
84.2%	94%	87%	87%	91%	88%	74%	83%	96%	91%	85%	82%	85%	88%	80%	96%	90%	79%	64%	77%	76%	75%
85.7%	90%	86%	91%	88%	84%	72%	92%	89%	88%	86%	90%	79%	88%	88%	88%	88%	86%	88%	76%	79%	83%
83.8%	89%	85%	85%	87%	86%	74%	89%	77%	84%	87%	86%	66%	82%	79%	97%	86%	76%	87%	85%	87%	85%
87.9%	96%	84%	90%	90%	89%	90%	96%	92%	91%	91%	88%	74%	94%	89%	88%	91%	84%	81%	79%	83%	85%
88.7%	96%	89%	94%	83%	97%	86%	92%	91%	86%	80%	90%	81%	89%	89%	93%	87%	92%	89%	89%	75%	95%
80.7%	90%	81%	80%	82%	85%	75%	76%	72%	81%	87%	83%	73%	83%	82%	89%	84%	78%	64%	81%	81%	88%
69.8%	81%	69%	77%	74%	69%	52%	67%	75%	70%	73%	62%	72%	71%	57%	75%	75%	65%	71%	65%	76%	70%
82.7%	83%	91%	81%	84%	88%	66%	87%	92%	85%	88%	76%	87%	86%	69%	90%	90%	86%	88%	68%	76%	76%
67.9%	73%	85%	71%	70%	75%	66%	73%	73%	55%	61%	69%	38%	69%	62%	73%	71%	57%	69%	72%	69%	74%
70.7%	63%	75%	67%	76%	84%	67%	60%	59%	67%	70%	80%	66%	65%	63%	66%	68%	82%	89%	70%	74%	74%
85.0%	89%	86%	93%	89%	90%	81%	84%	82%	84%	90%	81%	75%	90%	90%	90%	93%	81%	75%	81%	81%	79%
82.0%	83%	84%	80%	80%	86%	75%	84%	80%	83%	80%	75%	82%	80%	80%	87%	81%	84%	80%	89%	82%	88%
65.0%	64%	64%	67%	67%	61%	72%	64%	67%	64%	67%	72%	65%	67%	67%	61%	66%	64%	67%	59%	59%	62%
83.1%	86%	78%	81%	89%	94%	77%	74%	92%	89%	90%	78%	84%	84%	78%	87%	87%	84%	85%	69%	79%	81%
66.9%	73%	80%	63%	63%	58%	62%	56%	60%	59%	71%	72%	64%	83%	86%	54%	65%	64%	69%	83%	67%	53%
83.0%	84%	89%	90%	81%	81%	88%	92%	87%	81%	82%	81%	76%	84%	86%	84%	86%	84%	78%	76%	78%	75%
87.8%	94%	87%	97%	97%	84%	91%	93%	79%	85%	95%	87%	80%	94%	89%	94%	95%	87%	75%	88%	67%	86%
86.3%	87%	94%	94%	93%	92%	81%	92%	91%	92%	94%	82%	75%	94%	75%	96%	87%	77%	78%	78%	67%	93%
80.5%	90%	79%	87%	89%	84%	63%	89%	90%	85%	85%	79%	78%	85%	69%	92%	87%	80%	74%	69%	66%	71%
97.0%	97%	96%	100%	100%	94%	95%	96%	100%	97%	100%	95%	98%	100%	100%	95%	96%	96%	100%	91%	98%	93%
83.2%	88%	86%	94%	94%	95%	73%	91%	93%	82%	88%	83%	93%	85%	84%	94%	86%	78%	27%	76%	71%	86%
77.9%	76%	81%	74%	74%	76%	74%	79%	83%	80%	76%	79%	82%	79%	83%	86%	80%	80%	77%	72%	72%	73%
81.8%	93%	92%	76%	82%	89%	93%	78%	81%	79%	78%	85%	80%	78%	81%	77%	87%	79%	85%	76%	79%	69%

Model Similarity Dendrogram

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