	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	3rd 69.7%	9th 68.5%	7th 69.1%	1st 71.0%	6th 69.2%	19th 63.9%	4th 69.3%	12th 66.9%	10th 68.1%	8th 68.9%	11th 68.0%	20th 63.4%	14th 66.0%	16th 64.8%	2nd 70.1%	5th 69.3%	17th 64.7%	21st 62.1%	18th 64.1%	13th 66.4%	15th 65.7%
80.2%	77%	77%	88%	100%	77%	82%	74%	75%	90%	100%	90%	46%	75%	82%	87%	80%	75%	66%	88%		74%
66.2%	70%	58%	64%	74%	61%	73%	69%	64%	60%	64%	70%	70%	70%	65%	75%	66%	54%	66%	62%	61%	74%
49.0%	51%	53%	44%	55%	44%	55%	47%	54%	47%	47%	54%	54%	47%	54%	41%	51%	47%	48%	41%	54%	41%
65.0%	71%	60%	71%	71%	77%	53%	71%	71%	62%	71%	67%	65%	71%	39%	71%	75%	64%	63%	43%	70%	60%
71.8%	81%	70%	76%	76%	80%	70%	76%	72%	79%	79%	64%	64%	70%	68%	70%	64%	68%	64%	70%	66%	80%
84.3%	82%	82%		82%	79%		81%	68%	87%	87%	81%	88%	87%	80%	91%	84%	76%	84%	91%	100%	91%
76.7%	82%	77%	82%	82%	80%	75%	82%	76%	86%	82%	82%	68%	74%	68%	72%	82%	79%	78%	68%	61%	75%
73.0%	78%	79%	59%	63%	82%	65%	82%	59%	70%	82%	78%	70%	78%	65%	74%	76%	81%	80%	65%	60%	88%
84.5%	89%	88%	82%	82%	91%	78%	80%	89%	89%	82%	89%	80%	79%	83%	80%	89%	89%	87%	82%	83%
71.5%	84%	67%	65%	76%	58%	65%	66%	69%	69%	76%	74%	70%	84%	69%	74%	66%	56%	64%	87%	79%	83%
47.8%	54%	54%	54%	54%	46%	60%	54%	62%	47%	47%	48%	54%	31%	46%	40%	35%	42%	23%	62%	39%	52%
76.1%	75%	75%	83%	76%	87%	77%	71%	78%	89%	71%	76%	70%	71%	89%	78%	76%	72%	74%	76%	60%	74%
77.0%	87%	81%	87%	91%	83%	77%	74%	70%	75%	88%	76%	55%	73%	69%	88%	81%	75%	62%	88%	63%	73%
76.3%	68%	83%	74%	74%	89%	66%	86%	72%	89%	78%	74%	72%	74%	74%	74%	90%	78%	64%	87%	64%	73%
79.0%	89%	83%	89%	87%	71%	77%	78%	74%	78%	79%	89%	89%	71%	89%	82%	82%	74%	67%	74%	72%	64%
69.8%	66%	68%	66%	73%	68%	67%	68%	63%	68%	68%	77%	68%	66%	73%	72%	69%	67%	63%	68%	100%	68%
63.7%	76%	75%	91%	67%	63%	56%	63%	50%	58%	49%	69%	52%	48%	60%	82%	76%	48%	60%	61%	82%	52%
55.3%	60%	47%	50%	61%	60%	37%	52%	71%	61%	51%	47%	75%	61%	49%	50%	55%	61%	55%	45%	55%	58%
36.0%	37%	22%	43%	37%	78%	19%	31%	32%	29%	52%	31%	20%	31%	39%	61%	56%	37%	22%	9%	39%	31%
57.9%	64%	64%	60%	64%	60%	63%	60%	40%	60%	64%	55%	53%	60%	60%	61%	57%	52%	49%	52%	64%	53%
62.7%	58%	65%	58%	57%	62%	69%	65%	55%	67%	66%	73%	60%	68%	66%	62%	64%	56%	58%	60%		65%
71.1%	76%	73%	73%	73%	76%	75%	67%	62%	66%	78%	87%	55%	66%	73%	71%	75%	72%	60%	67%	78%	70%
58.1%	64%	53%	56%	59%	60%	62%	53%	62%	53%	62%	68%	55%	54%	60%	68%	55%	47%	59%	53%	53%	64%
66.5%	68%	71%	75%	75%	65%	73%	59%	68%	68%	74%	61%	48%	61%	68%	64%	68%	68%	62%	70%		64%
79.9%	87%	75%	73%	73%	87%	81%	87%	87%	87%	87%	69%	88%	88%	70%	81%	89%	88%	66%	73%	60%	81%
63.2%	58%	66%	71%		63%	76%	65%	51%	68%	63%	68%	63%	58%	66%	61%	56%	58%	54%	66%	82%	52%
60.3%	61%	57%	68%	68%	59%	47%	60%	77%	65%	61%	54%	52%	61%	58%	74%	57%	64%	48%	56%	54%	65%
45.8%	57%	47%	51%	60%	66%	22%	47%	48%	50%	41%	34%	34%	34%	33%	57%	58%	40%	43%	27%	53%	60%
71.4%	83%	91%	88%	88%	75%	67%	88%	61%	61%	61%	83%	73%	56%	66%	53%	66%	54%	55%	76%	82%
76.0%	77%	74%	77%	90%	90%	71%	100%	83%		71%	68%	70%	88%	63%	75%	69%	67%		64%		71%
50.0%	49%	50%	50%	50%	50%	48%	56%	48%	57%	45%	47%	48%	49%	50%	54%	56%	50%	56%	54%	47%	37%
83.0%	80%	78%	88%	76%	88%	75%	85%	77%	85%	85%	77%	77%	85%	77%	92%	80%	85%	84%	92%	85%	92%
48.4%	51%	53%	44%		44%	55%	47%	54%	47%	47%	54%	54%	47%	54%	41%	51%	47%	48%	41%	47%	41%
71.5%	74%	76%	74%	82%	54%	61%	80%	79%	78%	76%	76%	63%	74%	56%	76%	80%	72%	77%	54%		68%
67.0%	65%	75%	65%	65%	41%	87%	65%	87%	51%	70%	70%	53%	81%	87%	58%	57%	60%	67%	53%	70%	81%
60.5%	61%	64%	62%	62%	63%	56%	64%	67%	59%	68%	59%	61%	59%	52%	63%	66%	57%	52%	56%	58%	61%
76.3%	76%	86%	76%	81%	73%	65%	86%	87%	76%	62%	73%	87%	67%	74%	87%	82%	73%	65%	57%	82%	87%
60.7%	65%	63%	65%	65%	65%	67%	69%	65%	57%	69%	65%	48%	65%	57%	75%	65%		56%	60%	36%	36%
55.0%	59%	60%	50%	50%	54%	48%	60%	54%	59%	53%	59%	61%	50%	50%	58%	58%	54%	50%	52%	61%	55%
90.5%	88%	86%	96%	84%	96%	83%	92%	85%	92%	92%	85%	85%	92%	85%	100%	88%	92%	91%	100%	92%	96%
63.1%	64%	66%	60%	63%	63%	33%	67%	73%	71%	57%	61%	51%	63%	58%	69%	70%	70%	82%	55%	69%	61%
82.2%	90%	88%	84%	84%	84%	82%	90%	81%	84%	100%	66%	91%	82%	75%	87%	90%	79%	69%	82%	75%	63%
64.5%	43%	67%	69%	61%	62%	64%	61%	58%	67%	58%	75%	68%	67%	68%	67%	68%	71%	68%	68%	67%	58%

Model Similarity Dendrogram

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