	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 67.1%	2nd 67.4%	1st 67.5%	6th 64.8%	18th 60.9%	13th 63.0%	9th 64.2%	14th 62.8%	16th 61.2%	10th 64.1%	4th 65.7%	20th 59.4%	5th 65.7%	11th 63.9%	12th 63.9%	7th 64.6%	15th 62.7%	19th 59.6%	8th 64.5%	17th 61.1%	21st 57.5%
58.5%	61%	57%	64%	61%	48%	53%	56%	58%	51%	66%	58%	59%	58%	58%	60%	66%	55%	51%	65%	58%	66%
36.7%	32%	34%	36%	36%	33%	39%	30%	29%	20%	23%	47%	47%	33%	47%	36%	30%	71%	22%	48%	40%	38%
91.7%	92%	94%	97%	95%	75%	97%	84%	100%	84%	98%	92%	98%	92%	92%	92%	88%	92%	98%	88%	86%	92%
58.1%	64%	64%		55%	55%		54%	64%	63%		55%	55%	55%		65%		62%	62%		55%	44%
80.6%	85%	79%	92%	92%	77%	78%	85%	78%	81%	61%	77%	66%	74%	66%	81%	88%	78%	92%	89%	92%	81%
76.6%	74%	74%	71%	74%	71%	86%	82%	84%	86%	76%	74%	74%	86%	86%	74%	74%	87%	74%	75%	75%	51%
51.3%	59%	58%	60%	47%	53%	56%	55%	53%	56%	45%	59%	58%	50%	57%	46%	49%	41%	56%	57%	21%	42%
58.7%	67%	62%	71%	66%	63%	45%	71%	56%	55%	75%	57%	58%	61%	58%	58%	60%	55%	36%	53%	43%	63%
64.5%	56%	60%	68%	68%	77%	51%	69%	78%	67%	64%	62%	74%	64%	56%	58%	62%	65%	58%	63%	77%	58%
54.7%	64%		46%	65%	49%	65%			51%	55%	55%		55%		55%	49%	49%	49%	51%	45%	72%
49.0%	59%	60%	64%	49%	0%	66%	49%	51%	60%	23%	41%	38%	49%	59%	47%	51%	67%	34%	69%	51%	43%
71.5%	70%	75%	75%	70%	70%	71%	75%	71%	75%	71%	71%	80%	65%	70%	78%	68%	67%	70%	75%	67%	68%
74.0%	78%	84%	72%	80%	79%	80%	70%	67%	71%	75%	80%	54%	78%	78%	80%	71%	80%	82%	82%	78%	35%
53.8%	54%	56%	51%	47%	58%	61%	58%	56%	51%	48%	58%	55%	58%	55%	61%	56%	59%	43%	55%	47%	43%
39.3%	49%	48%	49%	46%	57%	49%	35%	33%	36%	50%	55%	29%	47%	45%	0%	43%		42%	52%	10%	12%
55.9%	57%	55%	63%	57%	47%	44%	58%	59%	51%	57%	58%	58%	51%	58%	59%	61%	55%	43%	53%	67%	62%
64.2%	77%	74%	77%	66%	54%	60%	58%	54%	60%	64%	64%	35%	67%	55%	75%	76%	66%	72%	61%	58%	75%
60.7%	72%	62%	71%	61%	45%	48%	59%	63%	56%	67%	58%	58%	63%	58%	69%	66%	59%	60%	58%	57%	64%
42.5%	49%	29%	46%	50%	48%	39%	53%	53%	34%	52%	53%	25%	50%	32%	50%	57%	33%	33%	37%	35%	34%
64.0%	67%	67%	73%	67%	58%	73%	63%	57%	50%	56%	70%	65%	74%	65%	71%	67%	47%	65%	67%	67%	55%
71.6%	63%	80%	80%	67%	74%	89%	79%	58%	76%	56%	74%	76%	74%	94%	59%	60%	74%	68%	73%	76%	53%
67.0%	70%	73%	71%	67%	69%	68%	67%	66%	65%	76%	70%	63%	73%	69%	66%	64%	63%	61%	68%	68%	51%
45.7%	44%	45%	44%	44%			57%	49%	52%	45%		37%		57%	48%	41%		36%	50%	36%
60.5%	70%	72%	63%	52%	67%	67%	56%	53%	53%	64%	71%	46%	64%	62%	66%	63%	63%	67%	73%	50%	28%
49.0%	56%	56%	48%	39%	54%	60%	56%	46%	39%	48%	56%	56%	58%	54%	46%	42%	36%	37%	53%		41%
60.1%	64%	67%	75%	64%	63%	50%	58%	57%	55%	61%	59%	60%	64%	58%	62%	56%	57%	51%	59%	64%	58%
70.2%	76%	76%	71%	71%	67%	41%	64%	76%	73%	86%	54%	69%	67%	53%	73%	75%	84%	75%	67%	74%	82%
60.0%	66%	63%	65%	65%	57%	60%	67%	61%	55%	77%	57%	55%	63%	54%	62%	59%	59%	57%	44%	51%	64%
56.9%	73%	77%	71%	75%		49%	64%	46%	47%	46%	56%	37%	60%	54%	64%	60%	37%			52%	57%
74.0%	67%	80%	75%	74%	71%	59%	73%	79%	88%	84%	82%	69%	84%	80%	75%	75%	38%	75%	80%	71%	74%
69.2%	73%	79%	74%	74%	76%	73%	79%	68%	62%	78%	68%	62%	69%	70%	69%	72%	67%	65%	65%	76%	34%
68.9%	68%	67%	64%	66%	86%	64%	77%	61%	77%	59%	68%	59%	68%	68%	68%	73%	68%	59%	73%	68%	86%
81.2%	84%	82%	84%	82%	63%	84%	71%	87%	71%	90%	80%	90%	80%	80%	80%	75%	80%	90%	75%	98%	80%
67.9%	67%	69%	68%	61%	67%	74%	75%	71%	64%	61%	70%	67%	63%	65%	72%	71%	70%	72%	60%	70%	69%
65.5%	80%	67%	64%	68%	40%	67%	41%	75%	64%	77%	75%	73%	71%	58%	66%	71%	57%	67%	58%	86%	51%
60.8%	60%	65%	67%	62%	58%	60%	64%	62%	52%	60%	67%	61%	60%	62%	56%	62%	63%	56%	57%	59%	64%
68.0%	83%	79%	67%	66%	86%	67%	60%	50%	59%	72%	67%	53%	78%	71%	69%	78%	76%	77%	69%	66%	35%
75.6%	84%	80%	91%	91%	90%	81%	87%	83%	84%	76%	90%	59%	90%	70%	74%	76%	59%	47%	76%	52%	47%
53.8%	64%	58%	59%	58%	56%	53%	59%	53%	56%	59%	49%	57%	59%	43%	49%	51%	48%	48%	42%	47%	62%
86.3%	83%	85%	83%	85%	95%	83%	96%	80%	96%	78%	87%	78%	87%	87%	87%	92%	87%	78%	92%	87%	87%
51.0%	55%	53%	60%	55%	39%	44%	53%	55%	51%	63%	60%	53%	55%	50%	57%	54%	55%	12%	50%	43%	53%
81.4%	87%	89%	83%	88%	73%	65%	78%	94%	75%	86%	81%	44%		91%	94%	87%	86%	90%	86%	81%	70%
64.9%	63%	76%	62%	62%	30%	62%	53%	43%	58%	63%	75%	84%	75%	75%	70%	73%	55%	75%	75%	64%	70%

Model Similarity Dendrogram

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