	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 66.2%	1st 67.3%	8th 65.8%	2nd 66.6%	13th 64.8%	19th 63.1%	11th 65.5%	6th 66.1%	18th 64.0%	17th 64.0%	7th 66.0%	16th 64.2%	3rd 66.5%	10th 65.5%	14th 64.4%	5th 66.1%	9th 65.7%	20th 62.6%	12th 64.9%	21st 62.2%	15th 64.3%
69.3%	66%	71%	71%	66%	71%	72%	81%	71%	66%	71%	69%	69%	69%	69%	70%	70%	64%	56%	69%	70%	74%
72.9%	66%	70%	72%	76%	67%	70%	64%	67%	66%	72%	76%	80%	78%	80%	73%	77%	80%	73%	76%	68%	80%
70.2%	63%	73%	75%	75%	67%	75%	67%	68%	67%	73%	78%	80%	63%	75%	68%	73%	71%	71%	67%	63%	63%
47.8%	49%	61%	48%	48%	45%	51%	54%	46%	44%	41%	49%	53%	53%	51%	38%	38%	59%	42%	51%	37%	45%
91.1%	88%	87%	93%	88%	97%	87%	88%	86%	93%	95%	91%	91%	92%	86%	93%	97%	97%	95%	90%	96%	83%
91.2%	95%	93%	95%	95%	93%	75%	93%	91%	90%	90%	90%	94%	90%	85%	96%	99%	94%	97%	81%	85%	95%
71.1%	69%	69%	73%	77%	78%	73%	71%	69%	70%	73%	69%	72%	71%	72%	72%	75%	71%	64%	65%	71%	69%
83.8%	84%	84%	73%	81%	77%	86%	82%	80%	89%	86%	86%	86%	86%	86%	84%	90%	80%	80%	87%	86%	86%
75.9%	76%	69%	65%	71%	82%	67%	71%	88%	83%	76%	77%	82%	82%	77%	74%	81%	82%	73%	82%	73%	62%
42.9%	42%	56%	41%	41%	43%	49%	49%	39%	37%	31%	47%	35%	47%	49%	29%	42%	55%	58%	49%	33%	28%
62.6%	63%	65%	65%	69%	60%	69%	61%	67%	67%	63%	64%	53%	64%	64%	68%	68%	60%	43%	64%	50%	68%
38.6%	40%	57%	32%	40%	44%	37%	34%	38%	36%	28%	52%	35%	38%	50%	25%	47%	48%	23%	50%	25%	32%
64.4%	65%	64%	62%	68%	67%	65%	57%	63%	65%	66%	67%	52%	64%	64%	66%	66%	64%	63%	70%	66%	68%
77.5%	82%	75%	76%	77%	69%	77%	85%	78%	79%	77%	70%	80%	82%	80%	83%	82%	71%	60%	73%	87%	84%
49.6%	49%	50%	48%	46%	53%	53%	47%	55%	54%	45%	49%	51%	54%	54%	49%	47%	53%	44%	46%	48%	47%
73.3%	67%	75%	70%	73%	81%	70%	76%	84%	76%	67%	76%	72%	76%	74%	62%	71%	76%	69%	74%	76%	75%
52.8%	56%	51%	57%	57%	57%	48%	50%	50%	50%	53%	50%	55%	55%	50%	57%	53%	50%	50%	55%	50%	55%
60.2%	59%	60%	58%	67%	67%	54%	63%	69%	57%	57%	57%	59%	57%	57%	63%	57%	57%	62%	59%	67%	58%
63.3%	73%	65%	68%	68%	28%	62%	71%	71%	58%	51%	72%	71%	77%	62%	44%	53%	54%	68%	66%	79%	68%
66.7%	68%	63%	69%	71%	69%	73%	64%	68%	62%	70%	67%	69%	72%	67%	61%	60%	65%	63%	69%	69%	61%
60.2%	67%	65%	62%	72%	66%	55%	65%	61%	62%	60%	58%	58%	62%	55%	63%	63%	62%	55%	55%	45%	53%
81.6%	84%	87%	84%	78%	84%	64%	89%	93%	90%	80%	80%	94%	87%	80%	81%	85%	85%	76%	64%	71%	78%
50.6%	60%	53%	55%	62%	45%	42%	51%	40%	39%	46%	59%	28%	42%	42%	61%	55%	48%	57%	59%	59%	59%
67.1%	67%	68%	69%	67%	67%	69%	58%	69%	69%	68%	70%	58%	69%	69%	68%	68%	65%	64%	68%	70%	69%
50.5%	50%	50%	54%	48%	54%	50%	48%	49%	51%	54%	48%	54%	52%	55%	48%	51%	51%	51%	46%	47%	49%
59.9%	60%	56%	60%	55%	59%	70%	54%	52%	59%	61%	64%	55%	60%	69%	57%	63%	64%	60%	60%	60%	59%
67.0%	65%	69%	69%	66%	69%	49%	68%	78%	67%	66%	56%	72%	70%	59%	66%	62%	74%	79%	67%	63%	72%
60.6%	66%	66%	63%	64%	63%	50%	68%	65%	57%	69%	64%	55%	60%	57%	64%	63%	59%	46%	59%	55%	60%
54.7%	55%	71%	65%	64%	40%	49%	63%	66%	37%	51%	59%	33%	54%	54%	58%	62%	44%	55%	59%	47%	62%
66.5%	61%	68%	72%	64%	62%	58%	60%	64%	67%	67%	71%	94%	65%	70%	62%	64%	72%	63%	69%	54%	70%
60.6%	65%	60%	64%	67%	60%	56%	58%	58%	59%	62%	64%	57%	66%	56%	63%	64%	57%	60%	62%	56%	59%
68.8%	75%	65%	63%	73%	71%	63%	71%	70%	71%	65%	60%	58%	75%	63%	75%	72%	67%	67%	71%	75%	75%
50.0%	44%	53%	55%	46%	48%	55%	48%	49%	48%	53%	57%	59%	44%	55%	51%	47%	51%	51%	48%	44%	44%
48.2%	49%	53%	49%	53%	52%	49%	53%	47%	50%	47%	46%	40%	48%	40%	50%	49%	48%	50%	43%	48%	49%
40.3%	46%	52%	42%	42%	22%	41%	26%	41%	39%	27%	47%	38%	53%	53%	33%	44%	39%	46%	52%	31%	33%
73.2%	78%	77%	77%	77%	67%	77%	79%	77%	69%	71%	72%	68%	75%	73%	74%	68%	72%	74%	73%	65%	75%
64.2%	68%	66%	66%	61%	68%	67%	68%	67%	69%	66%	59%	67%	63%	62%	65%	66%	63%	48%	69%	55%	65%
88.6%	85%	89%	92%	87%	91%	92%	96%	89%	88%	94%	96%	81%	87%	92%	86%	90%	90%	88%	81%	82%	85%
72.5%	76%	76%	78%	77%	78%	64%	80%	72%	72%	74%	69%	73%	72%	69%	76%	76%	72%	71%	64%	67%	66%
88.1%	95%	85%	82%	93%	91%	82%	91%	90%	91%	85%	80%	78%	95%	82%	87%	92%	87%	87%	91%	95%	91%
64.2%	75%	66%	67%	62%	65%	71%	62%	69%	58%	68%	68%	62%	62%	62%	68%	61%	65%	52%	62%	62%	62%
73.0%	74%	78%	69%	71%	77%	70%	77%	73%	70%	70%	73%	78%	72%	78%	73%	70%	77%	73%	72%	70%	68%
61.4%	63%	63%	60%	62%	73%	58%	55%	55%	60%	64%	64%	60%	55%	71%	64%	62%	64%	64%	55%	55%	62%

Model Similarity Dendrogram

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