	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 73.9%	6th 70.3%	2nd 72.6%	11th 69.4%	21st 62.1%	18th 65.5%	10th 69.5%	12th 69.1%	14th 68.8%	3rd 71.0%	5th 70.3%	19th 64.8%	7th 70.2%	16th 66.6%	4th 70.6%	9th 69.7%	17th 66.4%	20th 63.2%	13th 69.0%	15th 67.8%	8th 69.8%
59.9%	69%	66%	66%	62%	52%	53%	64%	64%	61%	59%	64%	71%	61%	59%	67%	55%	47%	53%	59%	50%	55%
65.4%	64%	64%	67%	63%	39%	76%	55%	61%	66%	55%	76%	77%	76%	80%	52%	63%	83%	68%	81%	67%	40%
91.5%	100%	85%	100%	96%	78%	92%	85%	92%	85%	92%	95%	92%	92%	95%	92%	94%	92%	95%	92%	96%	81%
81.0%	89%	70%	70%	76%	76%	70%	89%	89%	89%	89%	89%	76%	89%	66%	89%	82%	89%	74%	89%	76%	76%
66.1%	72%	59%	80%	66%	72%	70%	80%	69%	69%	61%	61%	61%	61%	59%	80%	57%	53%	33%	72%	53%	100%
68.0%	77%	70%	69%	69%	79%	70%	62%	70%	62%	62%	70%	70%	68%	60%	69%	68%	69%	76%	62%	56%	69%
80.4%	87%	87%	87%	77%	84%	78%	80%	87%	88%	87%	84%	69%	84%	67%	75%	77%	79%	84%	76%	77%	75%
57.6%	58%	58%	66%	63%	49%	41%	54%	58%	58%	72%	63%	54%	54%	56%	62%	63%	49%	71%	52%	54%	54%
73.1%	69%	69%	69%	69%	77%	56%	61%	78%	69%	77%	77%	85%	77%	68%	76%	76%	76%	81%	73%	69%	84%
71.8%	76%	76%	79%	79%	76%	76%	66%	52%	63%	75%	76%	76%	76%	76%	67%	76%	63%	55%	76%		76%
61.0%	67%	56%	60%	56%	41%	72%	67%	56%	56%	41%	60%	79%	49%	60%	52%	56%	73%	33%	89%	72%	85%
71.0%	73%	80%	73%	73%	67%	73%	68%	89%	89%	70%	68%	77%	63%	72%	68%	76%	61%	49%	73%	72%	56%
48.0%	42%	52%	66%	56%	37%	62%	48%	37%	48%	48%	61%	39%	61%	66%	39%	40%	37%	32%	62%	37%	37%
76.7%	89%	81%	84%	79%	78%	75%	82%	79%	89%	79%	81%	75%	77%	58%	74%	74%	75%	65%	87%	75%	54%
77.0%	76%	84%	73%	63%	72%	75%	66%	58%	66%	84%	84%	59%	76%	88%	92%	83%	81%	74%	92%	81%	90%
60.0%	68%	61%	69%	56%	62%	56%	62%	64%	55%	69%	62%	58%	61%	60%	68%	62%	56%	38%	53%	52%	67%
55.5%	72%	72%	68%	58%	63%	41%	56%	43%	56%	56%	56%	26%	56%	43%	63%	56%	57%	43%	51%	63%	67%
75.2%	82%	76%	76%	78%	90%	45%	72%	85%	74%	88%	64%	74%	74%	68%	86%	76%	81%	48%	59%	83%	100%
66.2%	74%	57%	65%	57%	38%	41%	76%	91%	69%	84%	69%	34%	84%	50%	76%	80%	61%	68%	56%	85%	76%
74.8%	83%	80%	80%	71%	72%	82%	81%	91%	71%	80%	66%	64%	82%	64%	73%	80%	73%	75%	75%	64%	64%
59.3%	58%	70%	70%	50%	29%	60%	70%	56%	66%	63%	72%	70%	62%	63%	49%	50%	56%	48%	60%	71%	53%
59.4%	63%	62%	62%	70%	70%	42%	62%	63%	61%	63%	42%	58%	62%	55%	68%	64%	62%	58%	42%	58%	60%
60.4%	53%	66%	53%	53%	53%	58%	66%	66%	66%	58%	58%	50%	63%	77%	66%	58%	66%	53%	66%	60%	60%
50.1%	52%	56%	56%	50%	42%	68%	52%	42%	52%	45%	62%	42%	52%	56%	39%	53%	42%	37%	70%	42%	42%
74.0%	74%	79%	85%	76%	78%	81%	85%	74%	84%	73%	83%	46%	78%	48%	66%	77%	73%	81%	78%	75%	59%
50.5%	56%	55%	55%	53%	42%	44%	49%	55%	51%	55%	50%	51%	55%	52%	44%	55%	47%	51%	52%	51%	38%
71.6%	80%	75%	79%	78%	83%	44%	65%	75%	71%	89%	54%	71%	71%	59%	75%	77%	72%	72%	60%	76%	78%
60.2%	69%	62%	62%	64%	38%	55%	62%	62%	49%	69%	62%	67%	62%	56%	60%	66%	62%	55%	60%	62%	61%
79.9%	92%	92%	83%	72%	79%	75%	79%	75%	100%	72%	89%	60%	75%	67%	92%	92%	59%	75%	100%	67%	83%
65.3%	73%	59%	76%	72%	61%	61%	77%	70%	56%	70%	59%	58%	69%	61%	70%	64%	69%	50%	61%	64%	72%
71.0%	75%	80%	75%	77%	48%	75%	79%	66%	75%	75%	66%	79%	75%	73%	77%	70%	67%	60%	61%	79%	59%
62.3%	57%	59%	57%	60%	78%	64%	64%	64%	71%	64%	61%	64%	64%	61%	71%	62%	64%	57%	64%	39%	64%
74.8%	81%	78%	81%	77%	59%	73%	73%	73%	66%	73%	76%	73%	73%	76%	66%	69%	73%	81%	73%	100%	77%
66.6%	68%	67%	71%	73%	73%	58%	64%	64%	68%	61%	63%	64%	64%	64%	80%	73%	69%	67%	56%	64%	67%
69.2%	83%	58%	69%	73%	44%	76%	64%	69%	72%	82%	77%	54%	77%	80%	77%	61%	44%	72%	62%	80%	80%
58.6%	65%	61%	66%	63%	35%	63%	59%	61%	47%	54%	61%	61%	61%	61%	51%	60%	61%	55%	59%	67%	59%
73.9%	75%	72%	75%	63%	63%	81%	69%	53%	69%	72%	90%	75%	72%	84%	69%	75%	77%	81%	75%	74%	88%
77.5%	100%	67%	85%	78%	72%	88%	89%	89%	85%	85%	71%	64%	78%	67%	83%	76%	73%	59%	78%	62%	79%
65.9%	74%	74%	70%	69%	44%	71%	67%	67%	65%	74%	67%	69%	65%	67%	70%	67%	59%	53%	61%	65%	65%
92.5%	100%	85%	100%	96%	78%	92%	92%	92%	85%	92%	95%	92%	92%	95%	92%	94%	92%	100%	92%	95%	92%
77.0%	84%	81%	75%	84%	48%	74%	84%	81%	75%	84%	78%	59%	84%	69%	90%	81%	72%	80%	69%	76%	90%
79.4%	81%	83%	72%	88%	83%	48%	81%	83%	73%	81%	83%	73%	81%	84%	83%	80%	80%	88%	72%	78%	92%
70.7%	77%	79%	79%	79%	67%	63%	63%	58%	67%	70%	79%	70%	61%	74%	79%	79%	61%	70%	69%	61%	79%

Model Similarity Dendrogram

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