	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
Score	2nd 74.5%	5th 72.5%	1st 74.7%	4th 73.1%	13th 67.9%	20th 65.1%	7th 71.8%	12th 69.7%	11th 70.2%	3rd 73.2%	9th 71.0%	15th 67.2%	6th 71.9%	17th 66.3%	8th 71.7%	10th 70.9%	19th 65.3%	18th 66.2%	14th 67.6%	16th 66.6%	21st 62.9%
84.9%	84%	88%	89%	68%	68%	67%	91%	97%	98%	82%	90%	84%	94%	81%	97%	93%	84%	84%	78%	93%	72%
60.0%	66%	63%	66%	66%	57%	67%	63%	68%	59%	57%	60%	66%	66%	65%	55%	57%	53%	38%	69%	57%	43%
78.1%	87%	68%	78%	85%	66%	79%	77%	81%	70%	81%	81%	86%	86%	79%	76%	82%	77%	74%	81%	68%
76.8%	79%	92%	78%	80%	69%	84%	79%	80%	72%	80%	85%	76%	78%	67%	69%	78%	73%	72%	74%		70%
65.4%	66%	61%	70%	77%	58%	71%	70%	58%	57%	57%	66%	73%	58%	58%	70%	64%	59%	57%	75%	84%	64%
67.1%	77%	70%	70%	71%	75%	53%	66%	73%	63%	66%	70%	58%	60%	62%	66%	66%	66%	74%	70%	62%	71%
77.6%	76%	83%	83%	83%	81%	84%	83%	82%	83%	83%	79%	73%	75%	76%	82%	79%	67%	73%	68%	76%	61%
65.9%	75%	70%	75%	73%	65%	47%	75%	65%	70%	75%	63%	60%	76%	63%	76%	65%	61%	50%	60%	60%	59%
79.5%	90%	93%	93%	95%	79%	62%	74%	78%	79%	84%	93%	93%	84%	90%	85%	78%	69%	78%	74%	49%	50%
72.7%	75%	74%	75%	73%	76%	76%	71%	59%	76%	75%	76%	76%	76%	76%	73%	67%	67%	62%	76%	76%	72%
69.0%	74%	78%	82%	77%	26%	78%	77%	76%	69%	74%	83%	76%	62%	61%	67%	66%	51%	42%	85%	75%	70%
74.6%	75%	82%	88%	70%	76%	74%	79%	72%	76%	87%	77%	63%	73%	80%	81%	76%	67%	66%	63%	68%	73%
57.3%	68%	63%	65%	62%	66%	50%	60%	54%	60%	57%	53%	57%	59%	53%	57%	53%	57%	49%	47%	57%	57%
62.9%	59%	66%	67%	61%	68%	68%	63%	65%	63%	65%	65%	54%	71%	54%	66%	63%	57%	56%	63%	64%	63%
74.7%	77%	72%	66%	66%	82%	85%	72%	62%	69%	75%	80%	69%	85%	85%	73%	79%	73%	79%	86%	79%	54%
60.1%	61%	66%	62%	62%	59%	51%	63%	56%	64%	67%	65%	52%	59%	47%	66%	56%	65%	67%	59%		55%
54.4%	61%	65%	70%	56%	56%	50%	72%	35%	56%	61%	65%	49%	47%	51%	52%	65%	35%	49%	52%	42%
55.6%	70%	58%	67%	74%	58%	33%	50%	67%	53%	63%	49%	56%	60%	38%	59%	58%	60%	60%	45%	51%	38%
71.3%	83%	66%	80%	65%	32%	52%	65%	84%	88%	90%	84%	47%	83%	55%	77%	74%	80%	70%	60%	80%	83%
78.7%	83%	84%	83%	71%	65%	67%	83%	82%	80%	84%	81%	65%	84%	71%	89%	83%	65%	84%	89%	68%	91%
65.6%	70%	71%	71%	68%	77%	48%	71%	62%	72%	72%	58%	58%	71%	65%	71%	64%	68%	47%	50%	69%	74%
74.3%	75%	80%	78%	74%	78%	70%	79%	78%	80%	76%	78%	73%	80%	77%	82%	75%	58%	67%	63%	73%	67%
67.2%	73%	67%	72%	69%	71%	69%	72%	63%	63%	66%	67%	62%	62%	63%	72%	67%	63%	68%	69%	69%	65%
74.6%	78%	74%	89%	77%	80%	71%	71%	70%	75%	75%	79%	69%	77%	75%	73%	81%	71%	65%	75%	71%	71%
62.7%	64%	63%	65%	67%	57%	66%	64%	64%	68%	63%	60%	60%	63%	64%	65%	62%	55%	56%	63%	71%	57%
60.0%	69%	55%	68%	69%	56%	48%	54%	64%	49%	69%	55%	60%	63%	55%	66%	66%	62%	73%	59%	64%	35%
70.3%	74%	74%	76%	79%	78%	52%	67%	77%	68%	82%	53%	68%	76%	62%	68%	75%	71%	81%	67%	78%	50%
68.8%	74%	76%	69%	78%	74%	41%	71%	74%	80%	67%	63%	60%	70%	56%	77%	77%	71%	67%	47%	76%	77%
76.3%	81%	90%	85%	85%	93%	70%	80%	68%	68%	70%	68%	70%	67%	67%	80%	76%	67%	75%	81%	85%	77%
52.0%	72%	63%	71%	71%	79%	32%	45%	59%	55%	59%	55%	51%	53%	32%	60%	55%	32%	31%	55%	31%	31%
72.1%	80%	78%	71%	75%	70%	71%	74%	68%	71%	76%	76%	75%	78%	77%	64%	69%	69%	72%	77%	71%	52%
84.4%	75%	95%	84%	78%	97%	84%	86%	81%	92%	81%	81%	76%	76%	84%	86%	80%	86%	89%	81%	95%
67.0%	69%	59%	69%	76%	57%	70%	68%	72%	62%	72%	72%	77%	77%	70%	63%	73%	68%	65%	72%	29%
68.6%	72%	71%	70%	76%	63%	64%	73%	69%	66%	74%	66%	65%	65%	70%	68%	71%	72%	69%	63%	65%	69%
77.2%	75%	76%	82%	78%	47%	79%	80%	83%	83%	81%	84%	84%	80%	72%	72%	82%	87%	84%	69%	57%	87%
72.6%	78%	75%	75%	79%	59%	69%	75%	75%	67%	88%	75%	65%	73%	65%	79%	71%	71%	75%	66%	72%
66.6%	75%	62%	59%	52%	80%	75%	59%	49%	59%	69%	76%	63%	76%	78%	62%	50%	81%	80%	76%	64%	53%
74.4%	85%	65%	85%	78%	82%	93%	86%	87%	85%	85%	65%	60%	79%	63%	82%	85%	60%	61%	80%	64%	33%
72.4%	81%	77%	82%	82%	59%	57%	82%	81%	81%	81%	59%	70%	83%	54%	75%	78%	68%	56%	55%	78%	82%
90.0%	92%	82%	92%	99%	80%	93%	91%	95%	84%	95%	95%	100%	100%	93%	91%	96%	91%	88%	95%	49%
69.9%	81%	77%	68%	70%	78%	65%	75%	73%	77%	70%	75%	66%	66%	70%	73%	79%	25%	73%	63%	68%	75%
67.3%	72%	68%	64%	68%	65%	65%	75%	63%	65%	70%	65%	65%	70%	69%	72%	65%	76%	55%	64%	73%	65%
52.4%	52%	57%	61%	61%	58%	51%	55%	29%	44%	45%	65%	59%	52%	56%	48%	48%	49%	66%	44%	48%

Model Similarity Dendrogram

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