	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 70.4%	12th 69.1%	4th 70.3%	6th 69.6%	8th 69.4%	17th 66.7%	7th 69.5%	18th 66.3%	9th 69.3%	11th 69.2%	5th 70.0%	20th 64.8%	9th 69.3%	14th 68.0%	1st 71.1%	2nd 70.5%	19th 65.7%	21st 62.6%	13th 68.3%	15th 67.7%	16th 66.8%
72.3%	73%	68%	85%	69%	52%	81%	74%	73%	73%	73%	68%	83%	68%	82%	71%	69%	64%	72%	88%	65%	67%
83.3%	78%	76%	87%	84%	54%	90%	88%	71%	85%	87%	85%	87%	85%	89%	87%	89%	85%	82%	89%	91%	80%
77.4%	79%	82%	83%	83%	83%	83%	75%	83%	75%	75%	83%	75%	75%	75%	75%	79%	75%	71%	75%	71%	71%
69.8%	78%	60%	68%	60%	75%	59%	68%	67%	67%	67%	73%	78%	78%	54%	76%	75%	72%	71%	73%	73%	73%
84.1%	82%	89%	76%	76%	82%	76%	76%	73%	82%	91%	100%	84%	91%	92%	76%	88%	91%	97%	84%	89%	72%
69.6%	69%	60%	60%	60%	60%	69%	69%	65%	75%	75%	75%	80%	75%	84%	69%	65%	65%	56%	75%	80%	75%
59.3%	57%	52%	61%	62%	59%	57%	59%	67%	60%	59%	59%	52%	59%	54%	66%	64%	65%	59%	57%	58%	60%
68.8%	75%	66%	78%	68%	67%	53%	78%	70%	74%	74%	70%	74%	62%	67%	70%	75%	60%	63%	58%	69%	74%
74.1%	70%	68%	66%	66%	75%	60%	66%	75%	74%	74%	80%	74%	80%	77%	78%	74%	80%	80%	80%	80%	80%
81.8%	77%	89%	82%	90%	82%	80%	82%	73%	87%	90%	89%	78%	100%	77%	85%	83%	82%	72%	77%	73%	69%
56.2%	64%	64%	64%	64%	50%	64%	62%	67%	57%	50%	50%	64%	48%	50%	50%	50%	31%	41%	67%		67%
73.7%	89%	74%	74%	74%	69%	75%	79%	75%	71%	75%	71%	69%	69%	69%	84%	75%	79%	72%	74%	60%	71%
48.2%	45%	45%	47%	53%	45%	61%	40%	45%	45%	45%	50%	45%	50%	50%	52%	44%	42%	49%	61%	54%	45%
65.2%	66%	68%	66%	60%	66%	63%	75%	54%	66%	66%	66%	75%	66%	68%	68%	67%	58%	66%	56%	64%	66%
80.8%	84%	89%	77%	77%	85%	80%	86%	80%	89%	77%	87%	89%	87%	87%	72%	83%	47%	82%	80%	86%	73%
81.9%	90%	90%	90%	81%	81%	73%	90%	80%	90%	90%	90%	65%	90%	86%	83%	75%	80%	79%	74%	82%	61%
68.5%	82%	82%	82%	76%	65%	64%	62%	64%	64%	64%	70%	64%	64%	62%	82%	87%	52%	45%	69%	62%	76%
58.7%	68%	60%	60%	60%	68%	43%	53%	65%	60%	62%	52%	39%	62%	54%	70%	62%	55%	63%	52%	53%	72%
31.6%	34%	12%	41%	34%	69%	8%	34%	34%	28%	34%	34%	12%	34%	20%	54%	48%	28%	18%	20%	34%	34%
65.0%	61%	64%	70%	70%	68%	74%	58%	62%	67%	67%	67%	67%	67%	58%	63%	58%	66%	61%	64%	67%	66%
52.1%	46%	52%	52%	52%	52%	67%	52%	37%	52%	52%	52%	64%	52%	64%	44%	48%	50%	42%	60%	44%	60%
65.5%	65%	65%	65%	73%	68%	72%	62%	51%	57%	68%	68%	57%	68%	68%	70%	67%	60%	62%	67%	68%	75%
50.2%	48%	49%	56%	47%	56%	50%	52%	53%	49%	50%	56%	49%	56%	56%	46%	47%	49%	46%	47%	49%	43%
77.3%	73%	77%	73%	71%	88%	79%	71%	74%	88%	71%	73%	65%	88%	88%	80%	70%	88%	81%	82%	68%	75%
69.7%	73%	73%	62%	63%	73%	71%	82%	63%	73%	73%	73%	73%	73%	87%	70%	75%	62%	61%	82%	58%	43%
66.3%	59%	78%	65%	67%	65%	75%	74%	60%	67%	67%	60%	70%	67%	69%	62%	66%	68%	67%	60%	67%	59%
81.7%	82%	83%	74%	90%	90%	58%	82%	80%	87%	90%	70%	70%	87%	81%	90%	89%	91%	84%	74%	75%	89%
80.0%	88%	88%	88%	88%	62%	70%	86%	71%	79%	82%	88%	88%	80%	70%	87%	90%	73%	78%	70%	77%	77%
72.3%	82%	91%	100%	82%	100%	56%	100%	68%	73%	59%	74%	43%	65%	65%	88%	74%	65%	43%	73%	74%	43%
66.2%	83%	67%	71%	75%	75%	74%	64%	70%	67%	62%	60%	41%	67%	62%	66%	62%	61%	55%	60%	83%	66%
67.9%	70%	64%	70%	70%	73%	75%	57%	54%	63%	70%	80%	53%	63%	73%	80%	76%	65%	50%	75%	63%	82%
83.0%	84%	78%	77%	77%	77%	77%	85%	77%	85%	85%	77%	85%	85%	85%	88%	85%	88%	88%	85%	88%	88%
48.3%	51%	53%	54%	54%	47%	54%	47%	54%	47%	47%	54%	47%	47%	47%	44%	44%	41%	44%	47%	47%	44%
79.3%	79%	80%	79%	73%	72%	74%	79%	89%	88%	71%	89%	76%	76%	73%	87%	89%	87%	80%	71%	79%	75%
63.6%	66%	68%	65%	71%	47%	69%	68%	67%	63%	71%	71%	47%	68%	66%	57%	68%	58%	60%	54%	79%	52%
45.4%	47%	47%	48%	49%	52%	43%	44%	47%	41%	47%	47%	47%	47%	40%	47%	44%	47%	35%	44%	47%	43%
68.4%	66%	68%	63%	58%	80%	73%	62%	55%	70%	70%	70%	59%	70%	70%	67%	80%	73%	50%	80%	82%	70%
62.8%	68%	66%	68%	68%	78%	72%	68%	58%	61%	68%	60%	53%	60%	63%	66%	68%	48%	51%	61%	53%	61%
69.6%	67%	73%	70%	90%	68%	70%	68%	68%	63%	71%	68%	66%	71%	71%	71%	73%	68%	54%	68%	60%	83%
90.3%	92%	85%	85%	85%	85%	85%	92%	85%	92%	92%	85%	92%	92%	92%	96%	96%	92%	96%	92%		96%
66.1%	70%	69%	75%	74%	75%	57%	74%	74%	71%	83%	75%	50%	52%	50%	84%	70%	70%	18%	58%	70%	69%
87.0%	90%	84%	90%	90%	90%	80%	90%	100%	90%	75%	81%	84%	84%	75%	83%	84%	89%	94%	100%	90%	84%
55.1%	58%	55%	57%	57%	58%	55%	57%	53%	66%	57%	58%	55%	53%	55%	55%	58%	53%	53%	55%	45%	45%

Model Similarity Dendrogram

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