	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	1st 75.5%	8th 73.7%	2nd 75.4%	12th 70.3%	4th 74.3%	19th 66.5%	10th 72.3%	3rd 74.4%	9th 72.8%	6th 73.9%	13th 69.8%	20th 66.3%	11th 71.4%	18th 67.9%	5th 74.2%	7th 73.9%	17th 68.1%	21st 65.9%	15th 68.6%	16th 68.3%	14th 69.1%
73.3%	70%	76%	74%	70%	63%	72%	75%	69%	76%	75%	83%	72%	75%	78%	76%	75%	69%	68%	78%	70%	75%
69.3%	81%	71%	82%	78%	60%	84%	73%	76%	64%	71%	64%	75%	69%	75%	73%	58%	44%	47%	74%	76%	60%
67.6%	81%	63%	81%	60%	60%	67%	70%	74%	64%	74%	72%	63%	68%	68%	63%	66%	56%	60%	63%	85%	62%
78.3%	80%	76%	76%	80%	79%	70%	83%	81%	80%	83%	76%	79%	83%	80%	85%	82%	73%	80%	58%	77%	83%
88.9%	94%	93%	90%	94%	95%	90%	91%	92%	87%	90%	91%	87%	83%	85%	96%	92%	88%	93%	90%	67%	78%
64.7%	72%	67%	66%	72%	68%	59%	59%	74%	63%	66%	66%	59%	66%	59%	62%	63%	60%	67%	66%	62%	63%
88.0%	88%	79%	92%	92%	86%	85%	93%	90%	93%	89%	88%	79%	83%	93%	89%	91%	89%	84%	81%	91%	93%
70.2%	85%	63%	72%	83%	97%	48%	71%	84%	73%	73%	68%	57%	71%	57%	79%	80%	81%	80%	54%	31%	68%
81.3%	71%	82%	77%	73%	86%	70%	79%	87%	87%	84%	80%	83%	83%	82%	73%	80%	79%	95%	82%	90%	85%
79.8%	82%	84%	89%	82%	79%	79%	79%	80%	79%	82%	79%	79%	78%	79%	84%	80%	69%	79%	79%	79%	76%
85.1%	89%	95%	90%	90%	77%	89%	89%	94%	93%	85%	84%	79%	85%	81%	94%	88%	68%	61%	88%	84%	84%
71.8%	77%	76%	75%	80%	84%	69%	69%	78%	80%	63%	66%	79%	55%	64%	68%	76%	65%	68%	74%	66%	76%
72.0%	61%	80%	76%	74%	78%	87%	72%	67%	67%	68%	85%	72%	73%	82%	68%	68%	62%	69%	76%	63%	63%
72.9%	80%	78%	80%	71%	71%	68%	74%	72%	73%	77%	72%	73%	76%	65%	79%	78%	81%	61%	79%	48%	75%
73.3%	74%	76%	78%	80%	72%	71%	79%	79%	72%	78%	68%	75%	76%	69%	79%	73%	66%	63%	76%	57%	78%
70.2%	79%	72%	79%	75%	77%	56%	70%	75%	70%	75%	65%	59%	75%	67%	78%	75%	71%	67%	64%	60%	65%
62.9%	75%	75%	75%	75%	77%	58%	74%	46%	67%	65%	66%	53%	54%	54%	65%	74%	51%	29%	66%	66%	56%
64.2%	75%	65%	76%	75%	77%	44%	61%	72%	61%	67%	59%	52%	66%	53%	67%	65%	70%	53%	60%	70%	61%
56.1%	57%	37%	58%	47%	80%	43%	47%	56%	60%	65%	41%	51%	68%	64%	69%	77%	52%	77%	42%	28%	60%
80.4%	82%	91%	86%	86%	67%	70%	89%	80%	79%	90%	85%	67%	89%	73%	90%	87%	67%	74%	90%	67%	80%
82.8%	72%	92%	92%	78%	91%	66%	86%	85%	91%	92%	83%	82%	93%	77%	87%	84%	76%	76%	67%	88%	80%
78.0%	83%	82%	85%	83%	79%	65%	83%	83%	83%	81%	74%	80%	79%	69%	76%	78%	77%	77%	68%	84%	69%
62.5%	64%	68%	68%	60%	70%	63%	68%	69%	67%	60%	67%	35%	60%	54%	67%	63%	63%	62%	67%		55%
78.7%	83%	83%	85%	81%	78%	75%	79%	83%	77%	83%	80%	81%	84%	81%	85%	84%	72%	48%	69%	81%	81%
67.5%	67%	70%	70%	67%	66%	69%	70%	76%	65%	71%	66%	52%	65%	65%	69%	76%	64%	73%	65%	64%	68%
65.8%	61%	68%	68%	60%	72%	64%	68%	59%	62%	71%	74%	78%	65%	76%	58%	67%	62%	62%	70%	59%	57%
56.8%	61%	60%	65%	63%	59%	55%	10%	60%	57%	64%	52%	56%	61%	56%	65%	62%	58%	53%	57%	60%	58%
53.6%	66%	61%	59%	60%	69%	36%	64%	68%	71%	57%	46%	42%	50%	38%	58%	66%	47%	37%	45%	41%	45%
75.7%	85%	86%	86%	92%	83%	63%	81%	68%	81%	62%	59%	85%	57%	60%	96%	83%	78%	56%	72%	85%	71%
64.0%	80%	64%	67%	76%	72%	59%	60%	69%	65%	68%	63%	61%	64%	51%	66%	57%	61%	46%	65%	71%	58%
62.8%	66%	67%	67%	73%	68%	61%	70%	73%	65%	67%	56%	47%	69%	58%	60%	61%	66%	58%	54%	58%	55%
64.3%	62%	71%	53%	0%	75%	68%	64%	61%	70%	61%	62%	71%	66%	66%	75%	68%	71%	71%	71%	71%	73%
49.0%	55%	47%	55%	0%	44%	50%	53%	56%	48%	56%	55%	47%	51%	51%	50%	50%	47%	48%	47%	66%	53%
73.1%	84%	73%	74%	82%	74%	67%	73%	78%	67%	75%	68%	67%	69%	63%	80%	79%	82%	79%	64%	67%	70%
70.9%	75%	76%	79%	74%	64%	67%	71%	76%	71%	64%	64%	65%	64%	74%	77%	76%	74%	71%	71%	74%	61%
72.3%	79%	72%	76%	80%	85%	62%	75%	75%	68%	80%	70%	52%	79%	59%	73%	75%	76%	74%	64%	74%	71%
76.6%	78%	78%	83%	92%	68%	70%	90%	93%	82%	80%	69%	81%	79%	73%	71%	68%	68%	53%	76%	87%	70%
81.1%	89%	86%	86%	86%	77%	90%	85%	87%	82%	85%	79%	65%	90%	70%	90%	93%	70%	70%	79%	52%	93%
54.0%	64%	58%	62%	64%	61%	49%	57%	70%	52%	65%	49%	48%	60%	44%	49%	47%	52%	42%	46%	57%	38%
88.8%	100%	90%	91%	0%	87%	94%	98%	99%	92%	99%	100%	90%	95%	95%	90%	93%	90%	91%	90%	92%	89%
63.1%	65%	68%	54%	65%	73%	52%	60%	62%	76%	66%	56%	41%	56%	60%	69%	71%	67%	71%	49%	71%	73%
79.7%	84%	81%	77%	80%	81%	69%	88%	80%	87%	87%	74%	78%	79%	83%	79%	78%	83%	74%	82%	67%	82%
64.9%	72%	70%	70%	70%	64%	65%	59%	44%	64%	64%	79%	54%	61%	70%	65%	69%	65%	66%	70%	63%	59%

Model Similarity Dendrogram

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