	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 72.5%	8th 71.3%	1st 74.3%	5th 71.8%	4th 72.1%	20th 62.7%	11th 70.2%	12th 70.0%	13th 69.3%	9th 71.1%	7th 71.6%	18th 66.0%	6th 71.6%	16th 67.2%	10th 70.4%	2nd 72.9%	14th 67.5%	19th 64.7%	17th 66.1%	15th 67.3%	21st 60.8%
83.8%	79%	89%	95%	79%	82%	62%	96%	85%	90%	82%	89%	86%	92%	86%	97%	94%	89%	57%	75%	72%
58.9%	66%	66%	63%	53%	49%	66%	55%	61%	56%	56%	65%	66%	66%	65%	50%	53%	45%	56%	69%	61%	50%
80.7%	79%	76%	78%	91%	79%	81%	77%	97%	77%	91%	97%	91%	86%	79%	72%	82%	72%	78%	76%	68%	68%
76.6%	78%	80%	78%	78%	80%	78%	78%	83%	73%	80%	79%	79%	76%	77%	73%	80%	79%	55%	78%	76%	70%
65.9%	71%	61%	70%	69%	66%	72%	70%	61%	66%	57%	61%	77%	66%	66%	66%	65%	63%	56%	68%	66%
67.9%	77%	71%	77%	77%	77%	66%	66%	73%	70%	66%	76%	51%	65%	62%	70%	66%	58%	66%	62%	62%
73.5%	74%	77%	76%	67%	74%	70%	73%	74%	69%	73%	79%	80%	78%	76%	78%	72%	70%	70%	81%	71%	61%
65.4%	70%	69%	75%	69%	66%	49%	71%	66%	61%	78%	68%	60%	70%	65%	62%	70%	67%	59%	57%	62%	59%
83.2%	83%	90%	93%	93%	84%	59%	77%	82%	79%	76%	90%	60%	93%	93%	90%	87%	81%	86%	79%	86%	87%
73.1%	75%	79%	73%	75%	71%	75%	73%	66%	71%	75%	78%	76%	78%	66%	75%	70%	63%	72%	81%	73%	71%
70.5%	74%	78%	82%	77%	63%	70%	77%	73%	79%	60%	66%	82%	59%	61%	74%	69%	61%	61%	76%	69%
72.9%	68%	75%	70%	70%	75%	75%	75%	76%	73%	69%	77%	64%	70%	81%	75%	73%	77%	70%	70%	79%	69%
56.9%	58%	56%	64%	72%	60%	51%	59%	64%	60%	62%	47%	58%	55%	54%	52%	58%	54%	55%	48%	57%	51%
55.2%	57%	55%	61%	60%	58%	49%	62%	60%	54%	48%	62%	62%	54%	58%	53%	61%	51%	65%	50%	40%	40%
73.7%	75%	79%	70%	66%	81%	79%	69%	55%	65%	71%	77%	69%	80%	81%	81%	85%	80%	64%	72%	90%	58%
59.0%	61%	62%	62%	61%	55%	43%	68%	67%	63%	62%	63%	57%	65%	54%	61%	58%	54%	55%	59%	53%	55%
56.9%	61%	65%	86%	65%	71%	38%	65%	37%	56%	61%	65%	35%	46%	51%	68%	68%	55%	31%	52%	61%
55.0%	70%	58%	58%	75%	76%	28%	45%	55%	53%	63%	49%	44%	53%	38%	53%	72%	59%	57%	45%	38%	67%
63.4%	64%	56%	65%	70%	89%	47%	58%	75%	52%	63%	66%	51%	59%	60%	91%	87%	54%	66%	56%	55%	48%
82.0%	87%	75%	89%	87%	91%	66%	87%	83%	87%	81%	85%	49%	85%	83%	92%	88%	87%	82%	86%	94%	59%
62.6%	61%	71%	71%	68%	62%	50%	67%	59%	62%	80%	67%	62%	69%	53%	62%	67%	57%	49%	51%	64%	62%
72.4%	66%	80%	88%	69%	72%	70%	79%	75%	79%	78%	78%	73%	78%	77%	59%	63%	73%	64%	67%	78%	54%
69.7%	72%	70%	69%	73%	67%	76%	72%	73%	67%	66%	69%	59%	69%	79%	73%	74%	61%	67%	69%	68%	71%
71.6%	77%	74%	92%	71%	70%	71%	67%	70%	73%	74%	83%	67%	75%	72%	81%	78%	72%	59%	67%	64%	46%
59.5%	53%	63%	67%	52%	58%	55%	60%	57%	55%	60%	60%	57%	64%	65%	65%	63%	61%	52%	62%	63%	57%
60.9%	71%	61%	65%	61%	64%	47%	53%	60%	59%	68%	55%	60%	66%	55%	64%	73%	66%	69%	51%	76%	35%
68.6%	74%	73%	75%	74%	74%	43%	64%	73%	68%	74%	64%	68%	78%	62%	77%	74%	74%	62%	65%	71%	53%
72.0%	74%	76%	68%	74%	82%	46%	71%	75%	80%	72%	76%	78%	74%	63%	80%	80%	71%	67%	57%	71%	78%
76.6%	89%	85%	85%	85%	81%	75%	75%	74%	80%	70%	75%	67%	68%	72%	77%	86%	68%	67%	81%	69%	79%
54.3%	76%	55%	68%	71%	85%	35%	53%	62%	46%	55%	55%	37%	55%	32%	63%	61%	53%	31%	46%	47%
70.1%	80%	79%	77%	68%	73%	78%	64%	67%	70%	67%	77%	73%	73%	77%	56%	66%	71%	66%	67%	73%	50%
79.3%	81%	86%	84%	71%	84%	81%	86%	66%	86%	71%	66%	71%	76%	84%	76%	80%	90%	84%	87%	95%	60%
73.9%	72%	67%	69%	82%	70%	72%	68%	88%	68%	82%	88%	82%	77%	70%	72%	73%	63%	69%	67%	59%	94%
72.5%	68%	73%	79%	63%	66%	66%	78%	78%	73%	83%	81%	70%	74%	72%	68%	74%	81%	74%	68%	71%	63%
66.7%	68%	64%	73%	64%	40%	56%	80%	83%	80%	81%	70%	44%	81%	52%	57%	80%	83%	80%	44%	71%	50%
69.9%	74%	75%	74%	77%	63%	62%	70%	82%	71%	80%	72%	62%	75%	65%	61%	69%	71%	64%	64%	73%	63%
66.4%	66%	65%	59%	52%	85%	79%	59%	49%	59%	52%	77%	59%	80%	78%	53%	61%	83%	87%	78%	70%	44%
80.7%	93%	77%	85%	85%	86%	93%	85%	82%	93%	91%	85%	74%	85%	59%	88%	84%	59%	62%	83%	65%
69.9%	80%	69%	77%	81%	79%	57%	81%	80%	78%	81%	59%	70%	81%	59%	80%	77%	59%	55%	51%	52%	61%
92.3%	95%	90%	92%	94%	93%	95%	91%	89%	91%	94%	89%	94%	100%	93%	100%	96%	86%	92%	90%	82%
74.0%	81%	73%	73%	75%	71%	61%	77%	80%	78%	82%	75%	82%	70%	70%	73%	73%	77%	76%	63%	74%	71%
66.4%	72%	68%	64%	62%	72%	62%	68%	68%	68%	76%	62%	77%	68%	69%	62%	62%	66%	57%	68%	62%	62%
51.2%	48%	57%	57%	61%	58%	44%	48%	29%	44%	45%	57%	56%	48%	56%	47%	61%	40%	66%	57%	44%

Model Similarity Dendrogram

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