	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	1st 69.9%	18th 64.0%	4th 69.1%	2nd 69.9%	16th 65.0%	19th 63.3%	7th 67.3%	7th 67.3%	12th 66.8%	11th 66.9%	15th 65.0%	21st 59.7%	6th 67.6%	20th 61.0%	3rd 69.2%	5th 68.3%	13th 66.5%	14th 65.2%	17th 64.1%	10th 67.1%	9th 67.1%
72.7%	68%	73%	85%	85%	65%	76%	73%	73%	73%	73%	73%	82%	73%	87%	73%	71%	44%	44%	82%	85%	69%
79.2%	80%	87%	87%	87%	55%	67%	89%	87%	87%	83%	67%	63%	87%	58%	87%	81%	76%	87%	89%	73%	86%
69.9%	80%	67%	67%	64%	67%	67%	75%	75%	64%	80%	67%	60%	60%	67%	80%	80%	80%	67%	60%	60%	80%
68.5%	78%	60%	68%	68%	62%	61%	78%	70%	68%	76%	78%	78%	78%	55%	69%	67%	73%	48%	78%	65%	61%
61.7%	61%	47%	68%	76%	47%	47%	76%	77%	68%	76%	47%	47%	68%	47%	68%	82%	68%	47%	47%	47%	84%
72.0%	69%	60%	60%	60%	60%	90%	75%	75%	75%	75%	75%	80%	90%	90%	65%	65%	82%	63%	75%	84%	45%
51.5%	59%	42%	45%	59%	61%	46%	54%	46%	51%	54%	54%	42%	37%	37%	62%	60%	57%	54%	48%	51%	62%
49.5%	56%	41%	57%	66%	50%	38%	50%	56%	50%	53%	41%	41%	49%	41%	68%	56%	46%	46%	38%	35%	62%
72.0%	75%	60%	56%	70%	80%	60%	66%	74%	66%	70%	70%	70%	70%	64%	84%	91%	84%	100%	60%	70%
78.0%	78%	69%	87%	74%	78%	78%	73%	78%	78%	74%	78%	74%	76%	74%	71%	100%	90%	64%	78%	77%	89%
51.0%	58%	57%	67%	58%	46%	62%	55%	57%	50%	42%	59%	67%	41%	31%	50%	41%	32%	31%	43%	68%	55%
72.3%	89%	67%	75%	89%	69%	77%	69%	69%	69%	69%	67%	69%	69%	69%	84%	71%	77%	63%	69%	69%	69%
52.3%	55%	55%	55%	55%	47%	61%	49%	53%	47%	47%	47%	64%	55%	47%	55%	55%	49%	38%	53%	47%	64%
69.7%	71%	63%	63%	68%	71%	77%	63%	71%	71%	75%	71%	71%	71%	71%	64%	70%	71%	68%	71%	71%	71%
68.0%	67%	62%	62%	67%	73%	67%	67%	72%	67%	67%	73%	68%	67%	67%	62%	62%	73%	78%	73%	67%	67%
74.4%	80%	69%	73%	80%	90%	69%	69%	74%	75%	81%	74%	49%	80%	80%	80%	80%	55%	76%	69%	80%	80%
58.6%	73%	62%	65%	65%	42%	64%	62%	45%	59%	56%	65%	71%	56%	65%	59%	68%	46%	56%	64%	46%	41%
60.0%	62%	52%	62%	62%	63%	44%	53%	58%	62%	53%	62%	44%	53%	62%	60%	62%	82%	82%	52%		69%
39.9%	34%	28%	34%	28%	61%	19%	34%	28%	34%	47%	47%	28%	41%	54%	61%	54%	41%	59%	12%	47%	47%
59.3%	62%	58%	70%	70%	56%	62%	58%	58%	58%	62%	56%	34%	60%	63%	56%	54%	61%	62%	63%	56%	67%
73.7%	75%	64%	88%	74%	70%	70%	78%	70%	70%	74%	84%	75%	75%	75%	75%	60%	64%	71%	70%	75%	91%
74.8%	76%	83%	76%	73%	75%	75%	75%	78%	76%	76%	75%	42%	76%	76%	88%	72%	65%	62%	76%	100%	76%
51.8%	43%	47%	38%	47%	66%	63%	52%	48%	49%	54%	54%	43%	65%	56%	47%	54%	57%	54%	47%	43%	60%
53.0%	54%	47%	54%	60%	47%	54%	60%	47%	52%	54%	47%	47%	74%	47%	47%	54%	62%	60%	52%	47%	47%
78.0%	87%	75%	75%	87%	71%	71%	75%	80%	87%	71%	71%	87%	87%	71%	78%	75%	91%	75%	71%	83%	71%
66.7%	68%	62%	62%	62%	76%	65%	68%	67%	63%	63%	61%	70%	78%	67%	63%	78%	65%	67%	65%	63%	67%
82.6%	100%	71%	90%	90%	90%	73%	73%	85%	85%	87%	68%	73%	85%	73%	78%	85%	100%	72%	85%		90%
67.6%	66%	79%	79%	71%	68%	42%	65%	77%	77%	71%	67%	59%	79%	42%	78%	82%	59%	74%	62%	65%	57%
74.5%	82%	91%	100%	100%	68%	62%	91%	74%	71%	64%	83%	43%	70%	43%	80%	73%	73%	69%	79%	83%	65%
64.5%	83%	62%	74%	74%	61%	54%	62%	63%	63%	62%	60%	60%	62%	59%	74%	67%	62%	67%	60%	60%	66%
82.4%	88%	88%	91%	82%	80%	100%	82%	82%	73%	78%	78%	87%	88%	100%	75%	73%	69%	75%	88%	78%	75%
74.6%	66%	66%	77%	77%	92%	92%	77%	81%	85%	67%	60%	60%	60%	60%	66%	69%	69%	92%	92%	92%	66%
42.3%	47%	47%	41%	41%	34%	34%	47%	48%	41%	47%	41%	34%	47%	34%	47%	47%	47%	41%	34%		47%
69.7%	79%	74%	79%	79%	57%	68%	60%	78%	79%	79%	60%	56%	60%	55%	90%	77%	74%	72%	54%	60%	74%
66.7%	75%	66%	75%	71%	47%	71%	57%	90%	54%	57%	47%	47%	71%	79%	71%	71%	90%	60%	79%	57%	66%
48.6%	47%	54%	52%	52%	47%	40%	53%	47%	47%	52%	47%	50%	54%	45%	50%	47%	45%	47%	45%	53%	47%
73.3%	70%	74%	70%	70%	73%	74%	70%	59%	82%	70%	78%	78%	73%	74%	77%	55%	78%	78%	75%	78%	84%
57.7%	66%	57%	60%	60%	68%	61%	66%	46%	57%	60%	53%	55%	57%	47%	66%	66%	60%	58%	47%		45%
72.8%	87%	79%	87%	87%	52%	62%	87%	74%	74%	83%	83%	59%	74%	67%	74%	74%	62%	72%	68%	68%	55%
81.0%	76%	76%	88%	76%	92%	92%	92%	92%	92%	76%	67%	67%	67%	67%	76%	76%	76%	92%	92%	92%	76%
66.8%	64%	54%	72%	75%	92%	32%	72%	72%	69%	72%	100%	40%	75%	31%	70%	74%	63%	83%	42%	75%	75%
85.9%	90%	100%	81%	90%	71%	81%	90%	84%	90%	82%	90%	80%	90%	69%	90%	89%	91%	83%	90%	81%	92%
56.5%	61%	58%	58%	55%	53%	53%	55%	57%	66%	66%	51%	55%	58%	58%	58%	51%	51%	48%	58%		60%

Model Similarity Dendrogram

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