	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	4th 70.2%	3rd 71.1%	1st 71.7%	11th 67.0%	17th 64.4%	12th 66.8%	6th 69.2%	10th 67.3%	13th 66.0%	16th 64.7%	2nd 71.1%	19th 64.1%	8th 67.8%	5th 69.5%	14th 66.0%	9th 67.5%	15th 65.2%	21st 62.2%	7th 68.8%	18th 64.2%	20th 63.3%
63.1%	67%	65%	73%	63%	58%	52%	74%	77%	73%	63%	65%	55%	65%	62%	58%	54%	46%	48%	66%	80%	61%
60.8%	61%	63%	64%	65%	35%	70%	54%	65%	57%	47%	65%	74%	65%	73%	63%	64%	54%	54%	76%	59%	48%
72.0%	77%	72%	69%	72%	57%	72%	72%	80%	62%	84%	77%	77%	67%	77%	84%	72%	72%	67%	67%	67%	67%
71.3%	83%	83%	64%	64%	78%	80%	83%	78%	74%	63%	64%	63%	64%	64%	78%	76%	64%	63%	83%	64%	64%
75.9%	69%	79%	76%	66%	89%	64%	69%	83%	76%	75%	82%	72%	89%	89%	75%	85%	78%	80%	69%	78%	50%
85.2%	83%	86%	76%	83%	75%	92%	86%	77%	89%	89%	83%	92%	89%	99%	82%	77%	87%	78%	92%	92%	83%
71.5%	75%	75%	77%	71%	54%	70%	75%	75%	70%	72%	76%	70%	82%	81%	70%	76%	60%		72%	66%	63%
76.4%	81%	85%	88%	70%	70%	59%	80%	84%	73%	73%	85%	86%	76%	84%	69%	71%	86%	51%	75%	85%	74%
79.8%	76%	75%	88%	88%	80%	78%	100%	100%	94%	71%	76%	92%	71%	79%	73%	62%	75%	73%	88%	73%	64%
62.8%	66%	66%	66%	66%	62%	77%	58%	57%	64%	64%	68%	63%	59%	71%	66%	66%	55%	49%	66%	46%	64%
70.9%	80%	77%	80%	80%	72%	80%	77%	73%	73%	54%	77%	67%	58%	67%	64%	67%	52%	65%	77%	77%	72%
76.2%	87%	77%	74%	77%	73%	72%	77%	77%	77%	80%	69%	79%	79%	76%	67%	72%	67%	75%	87%	77%	82%
76.8%	66%	83%	86%	81%	74%	85%	67%	70%	82%	58%	90%	73%	79%	73%	60%	74%	79%	78%	76%	89%	90%
41.8%	50%	59%	52%	29%	30%	59%	62%	53%	38%	40%	44%	47%	27%	47%	37%	41%	25%	41%	50%	19%	28%
70.9%	75%	75%	66%	71%	77%	87%	57%	52%	56%	66%	82%	50%	66%	69%	80%	79%	78%	71%	74%	76%	82%
69.6%	72%	75%	83%	69%	48%	66%	82%	81%	74%	71%	79%	56%	76%	76%	65%	69%	65%	65%	73%	51%	65%
74.0%	83%	83%	94%	70%	86%	55%	70%	55%	70%	70%	83%	53%	69%	67%	88%	74%	74%	91%	77%	65%	76%
54.6%	62%	50%	54%	69%	69%	20%	45%	52%	46%	58%	56%	61%	77%	39%	62%	54%	58%	59%	38%	46%	71%
40.9%	41%	30%	54%	42%	63%	28%	53%	33%	41%	33%	47%	41%	36%	24%	55%	65%	41%	23%	31%	42%	36%
70.3%	81%	56%	73%	79%	77%	69%	73%	71%	69%	81%	72%	82%	80%	75%	74%	73%	66%	64%	70%	31%	61%
61.9%	61%	70%	74%	67%	54%	83%	80%	63%	65%	56%	80%	58%	70%	78%	46%	58%	41%	42%	72%	44%	38%
55.0%	49%	67%	68%	45%	51%	81%	52%	46%	59%	39%	59%	43%	51%	71%	32%	57%	71%	49%	74%	65%	27%
55.1%	62%	62%	50%	55%	54%	57%	50%	56%	50%	53%	50%	50%	68%	53%	59%	55%	59%	52%	50%	56%	56%
77.6%	82%	70%	72%	86%	82%	64%	88%	90%	82%	90%	82%	46%	90%	84%	85%	82%	70%		57%	80%	70%
44.4%	46%	57%	50%	41%	32%	58%	59%	57%	48%	32%	59%	46%	33%	47%	32%	32%	36%		53%		25%
55.2%	58%	64%	67%	44%	43%	70%	72%	58%	64%	57%	59%	30%	52%	73%	44%	47%	39%	54%	72%	57%	36%
57.9%	59%	63%	69%	58%	63%	47%	62%	59%	59%	66%	60%	58%	63%	62%	58%	55%	56%	48%	60%	43%	48%
73.3%	75%	77%	79%	77%	62%	60%	79%	75%	63%	77%	75%	83%	75%	74%	75%	75%	80%	65%	53%	77%	84%
74.6%	95%	80%	95%	95%	83%	70%	74%	73%	73%	64%	72%	54%	65%	71%	77%	80%	67%	70%	70%	73%	65%
65.3%	86%	69%	69%	72%	77%	32%	59%	77%	58%	69%	65%	60%	69%	64%	73%	69%	82%	27%	73%	60%	61%
53.4%	51%	64%	54%	39%	62%	64%	45%	42%	44%	37%	72%	39%	45%	55%	42%	56%	69%	64%	60%	40%	77%
55.5%	51%	56%	59%	56%	72%	56%	56%	48%	67%	45%	51%	51%	61%	51%	46%	51%	55%	51%	61%	61%	61%
72.5%	77%	72%	69%	72%	57%	72%	72%	80%	62%	84%	77%	77%	67%	77%	77%	80%	73%	77%	67%	67%	67%
75.7%	80%	79%	79%	53%	65%	76%	82%	85%	75%	83%	82%	82%	86%	74%	80%	76%	83%	73%	64%	59%	74%
64.7%	68%	64%	72%	72%	31%	73%	67%	61%	68%	71%	62%	72%	64%	62%	68%	67%	60%	66%	55%	72%	63%
59.8%	65%	64%	63%	51%	39%	76%	61%	66%	53%	51%	63%	70%	63%	68%	43%	58%	65%	52%	76%	52%	56%
65.0%	65%	66%	65%	50%	83%	72%	56%	41%	54%	65%	65%	49%	56%	64%	71%	73%	64%	75%	72%	85%	73%
85.4%	89%	96%	89%	92%	86%	88%	83%	92%	89%	89%	88%	84%	93%	80%	88%	91%	70%	55%	92%	67%	93%
55.0%	46%	64%	65%	54%	55%	75%	53%	44%	48%	46%	65%	52%	52%	66%	48%	49%	62%	56%	59%	58%	38%
92.3%	89%	94%	98%	94%	89%	94%	94%	85%	95%	82%	89%	89%	100%	89%	83%	82%	93%	100%	100%	100%	100%
75.2%	77%	77%	78%	82%	58%	68%	82%	83%	75%	71%	82%	71%	78%	81%	76%	81%	79%		63%	70%	72%
61.2%	66%	67%	63%	63%	52%	39%	59%	56%	56%	66%	74%	56%	63%	71%	69%	63%	67%	67%	59%	55%	55%
82.2%	88%	100%	77%	88%	94%	63%	77%	62%	73%	78%	88%	83%	77%	83%	94%	94%	79%	88%	88%	72%	80%

Model Similarity Dendrogram

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