	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 67.3%	4th 66.7%	2nd 68.5%	1st 68.7%	21st 59.2%	16th 62.0%	11th 64.0%	13th 63.2%	17th 61.4%	5th 66.5%	10th 64.5%	19th 60.7%	8th 65.2%	15th 62.4%	7th 65.2%	6th 65.5%	14th 62.5%	18th 61.2%	9th 64.5%	20th 60.4%	12th 63.3%
59.5%	64%	60%	65%	68%	49%	53%	58%	62%	51%	68%	59%	60%	61%	58%	64%	61%	59%	58%	53%	53%	66%
35.7%	30%	30%	36%	47%	0%	43%	24%	36%	31%	25%	55%	43%	51%	47%	46%	35%	24%	30%	40%	47%	29%
86.9%	92%	86%	88%	95%	75%	89%	84%	84%	75%	89%	92%	92%	89%	92%	84%	86%	91%	92%	88%	86%	75%
61.6%	64%	66%	71%	55%	55%	54%	64%	71%	64%	55%	64%	55%	55%	70%	55%	73%	52%	69%	71%	55%	55%
82.1%	85%	79%	85%	89%	92%	86%	92%	89%	81%	78%	83%	71%	89%	77%	82%	83%	81%	64%	85%	72%	81%
79.5%	74%	74%	71%	74%	74%	86%	89%	87%	89%	76%	74%	87%	87%	86%	70%	74%	75%	74%	76%	87%	86%
49.1%	50%	44%	55%	58%	42%	37%	50%	55%	54%	44%	50%	55%	44%	44%	46%	57%	58%	54%	54%	42%	39%
61.5%	71%	65%	71%	77%	75%	45%	63%	57%	58%	80%	63%	58%	58%	47%	66%	61%	65%	52%	58%	43%	59%
66.5%	64%	65%	56%	58%	64%	51%	67%	70%	67%	78%	68%	66%	70%	56%	64%	62%	72%	87%	70%	68%	74%
56.4%	58%	80%	61%	72%	55%	55%	46%	43%	55%	61%	55%	55%	55%	55%	51%	51%	51%	49%	55%	55%	66%
50.3%	59%	60%	59%	59%	24%	66%	64%	49%	41%	41%	49%	64%	41%	38%	55%	54%	41%	32%	65%	75%	21%
71.1%	70%	73%	71%	71%	80%	71%	75%	70%	71%	75%	71%	80%	65%	70%	63%	67%	50%	75%	71%	75%	80%
72.8%	55%	76%	85%	85%	76%	100%	80%	58%	64%	76%	90%	57%	76%	82%	57%	75%	57%	80%	89%	53%	57%
56.0%	54%	54%	54%	65%	49%	64%	54%	65%	54%	65%	58%	56%	54%	64%	62%	55%	46%	50%	46%	51%
45.8%	55%	46%	46%	46%	49%	49%	43%	32%	38%	51%	51%	29%	55%	47%	49%	46%	42%	44%	55%	43%	46%
56.9%	58%	55%	63%	57%	67%	41%	58%	59%	56%	59%	49%	47%	47%	53%	65%	60%	58%	62%	47%	67%	67%
60.1%	77%	77%	76%	67%	45%	48%	58%	45%	60%	60%	64%	31%	60%	55%	64%	64%	58%	47%	64%	67%	75%
63.8%	67%	58%	77%	67%	64%	57%	58%	65%	53%	80%	58%	58%	58%	58%	69%	60%	62%	67%	71%	58%	75%
56.1%	62%	53%	46%	53%	48%	45%	70%	76%	56%	70%	53%	32%	76%	58%	53%	54%	54%	42%	50%	51%	76%
59.7%	63%	66%	66%	66%	49%	57%	66%	64%	55%	66%	56%	49%	66%	47%	71%	66%	57%	55%	56%	49%	64%
70.5%	63%	66%	79%	56%	74%	75%	74%	64%	79%	66%	85%	76%	79%	94%	67%	56%	65%	56%	79%	76%	51%
69.9%	71%	75%	75%	76%	79%	68%	73%	67%	64%	75%	70%	63%	64%	67%	75%	71%	66%	63%	68%	66%	72%
47.4%	44%	41%	50%	44%	52%	52%	48%	49%	50%	51%	50%	51%	45%	46%	51%	45%	43%	41%	52%	37%	54%
64.4%	70%	72%	72%	65%	65%	71%	54%	51%	59%	72%	75%	58%	72%	62%	58%	69%	70%	58%	64%	58%	58%
57.2%	58%	61%	64%	56%	58%	61%	64%	56%	53%	58%	51%	58%	64%	30%	52%	50%	70%	53%	58%	70%
57.8%	64%	59%	64%	64%	48%	40%	59%	57%	51%	66%	57%	60%	61%	55%	65%	65%	65%	46%	61%	59%	47%
64.1%	76%	71%	71%	71%	69%	42%	54%	76%	68%	54%	48%	69%	64%	50%	69%	67%	76%	53%	58%	67%	74%
63.3%	71%	67%	71%	74%	40%	57%	71%	73%	51%	80%	63%	58%	58%	47%	65%	65%	57%	53%	51%	63%	94%
55.1%	67%	71%	75%	86%	54%	54%	64%	54%	56%	46%	37%	37%	36%	46%	64%	55%	37%	51%	56%
72.7%	72%	77%	72%	74%	65%	61%	63%	81%	77%	75%	76%	63%	64%	79%	81%	76%	77%	68%	80%	71%	75%
73.2%	76%	88%	74%	80%	75%	66%	67%	63%	74%	88%	68%	65%	70%	74%	80%	77%	72%	70%	70%	78%	62%
71.7%	68%	75%	73%	66%	86%	71%	77%	77%	86%	71%	68%	68%	71%	68%	68%	74%	69%	68%	73%	48%	81%
74.7%	80%	73%	75%	82%	63%	77%	71%	71%	63%	77%	80%	80%	77%	80%	71%	80%	79%	80%	75%	63%	71%
56.2%	69%	53%	66%	65%	55%	48%	49%	55%	58%	48%	54%	49%	49%	55%	65%	64%	63%	49%	52%	49%	65%
70.5%	90%	69%	89%	86%	40%	78%	54%	58%	59%	72%	54%	86%	85%	73%	80%	73%	69%	88%	64%	54%	59%
60.8%	67%	62%	67%	70%	33%	76%	55%	65%	54%	66%	67%	62%	65%	63%	49%	64%	61%	52%	60%	66%	52%
70.0%	85%	74%	73%	77%	90%	62%	54%	50%	56%	70%	78%	53%	69%	76%	74%	83%	80%	83%	75%	53%	55%
75.1%	85%	75%	81%	84%	97%	81%	87%	84%	87%	76%	80%	59%	90%	66%	66%	77%	57%	61%	76%	61%	47%
54.0%	62%	59%	51%	60%	24%	63%	59%	44%	59%	71%	52%	57%	59%	49%	59%	55%	59%	43%	45%	52%	52%
89.5%	87%	94%	92%	85%	95%	90%	96%	96%	95%	90%	87%	87%	90%	87%	96%	93%	88%	87%	92%	66%	87%
53.0%	53%	51%	51%	55%	39%	58%	56%	55%	48%	65%	53%	43%	66%	50%	57%	54%	59%	57%	44%	46%	52%
81.7%	83%	90%	83%	86%	64%	55%	83%	86%	64%	70%	83%	90%	86%	91%	89%	87%	79%	94%	86%	86%
64.9%	63%	78%	75%	63%	50%	61%	55%	47%	58%	55%	75%	73%	61%	70%	67%	72%	72%	76%	72%	50%	70%

Model Similarity Dendrogram

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