	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	2nd 77.7%	3rd 77.3%	1st 78.4%	5th 77.0%	10th 75.5%	17th 71.3%	13th 73.8%	16th 71.9%	15th 72.7%	8th 75.8%	4th 77.2%	19th 71.0%	9th 75.5%	14th 72.9%	6th 76.8%	7th 76.0%	11th 74.7%	21st 67.7%	12th 74.0%	18th 71.2%	20th 68.7%
75.8%	74%	78%	82%	71%	77%	67%	82%	85%	80%	77%	78%	74%	74%	83%	73%	73%	69%	63%	77%		78%
71.1%	70%	74%	73%	73%	69%	73%	73%	65%	67%	70%	76%	70%	72%	71%	69%	69%	70%	67%	73%	80%	69%
74.0%	77%	68%	78%	77%	72%	72%	68%	70%	70%	80%	78%	65%	74%	70%	80%	74%	77%	83%	58%	63%	100%
89.8%	85%	90%	89%	89%	91%	84%	90%	86%	86%	95%	97%	90%	92%	88%		89%	90%	93%	87%	90%	95%
87.1%	85%	89%	85%	92%	93%	82%	93%	92%	88%	79%	89%	89%	90%	85%	89%	87%	88%	82%	91%	72%	89%
85.3%	96%	91%	93%	93%	82%	86%	84%	77%	80%	87%	83%	88%	87%	77%	92%	90%	81%	83%	88%	72%	82%
87.0%	93%	94%	90%	88%	96%	83%	96%	92%	86%	87%	94%	92%	87%	82%	86%	89%	87%	58%	87%	83%	76%
77.6%	83%	78%	74%	84%	80%	47%	72%	90%	88%	82%	82%	80%	80%	76%	88%	89%	77%	53%	68%	79%	79%
81.1%	89%	84%	89%	92%	79%	68%	71%	75%	76%	81%	88%	83%	92%	88%	83%	86%	85%	75%	84%	78%	58%
91.2%	86%	91%	95%	92%	87%	93%	92%	87%	90%	97%	94%	95%	92%	91%	92%	92%	92%	90%	90%	86%
76.0%	90%	82%	76%	87%	67%	91%	85%	88%	82%	68%	83%	71%	66%	68%	75%	62%	70%	50%	94%	88%	52%
85.2%	96%	85%	80%	93%	86%	86%	80%	83%	78%	83%	87%	86%	85%	85%	89%	87%	82%	82%	86%		85%
69.8%	62%	74%	64%	72%	72%	81%	65%	60%	70%	64%	76%	54%	75%	73%	73%	64%	68%	75%	79%	75%
62.0%	70%	64%	57%	59%	65%	71%	64%	64%	53%	61%	69%	63%	67%	64%	58%	64%	73%	50%	65%	47%	53%
69.5%	76%	74%	67%	67%	75%	72%	59%	56%	60%	73%	69%	55%	66%	64%	75%	78%	74%	78%	76%	76%
77.7%	81%	83%	84%	81%	72%	61%	78%	81%	77%	82%	78%	73%	82%	71%	79%	83%	72%	78%	76%	77%	82%
60.6%	71%	79%	81%	64%	59%	47%	59%	47%	60%	63%	61%	44%	51%	52%	66%	70%	65%	45%	60%	59%	70%
67.4%	75%	66%	70%	80%	73%	42%	53%	75%	63%	73%	58%	59%	73%	55%	72%	75%	77%	65%	61%	81%	70%
43.5%	47%	31%	51%	44%	65%	31%	42%	38%	43%	41%	45%	34%	46%	36%	75%	54%	41%	34%	29%
71.4%	78%	82%	79%	73%	67%	76%	76%	62%	65%	72%	75%	73%	68%	74%	79%	74%	58%	62%	80%	80%	46%
75.0%	73%	80%	82%	74%	80%	74%	84%	68%	79%	79%	84%	78%	78%	79%	67%	70%	64%	62%	79%	69%	72%
68.4%	67%	75%	71%	65%	69%	70%	74%	64%	67%	73%	75%	61%	78%	72%	65%	65%	74%	66%	74%	70%	41%
72.4%	67%	71%	76%	64%	75%	77%	66%	74%	75%	66%	77%	79%	75%	82%	66%	71%	70%	74%	72%	75%	69%
79.6%	85%	87%	86%	86%	84%	75%	77%	74%	83%	82%	87%	71%	85%	81%	85%	88%	84%	74%	76%	79%	42%
55.0%	56%	69%	58%	45%	63%	71%	56%	55%	55%	50%	66%	52%	67%	55%	48%	52%	43%	44%	62%	46%	43%
65.1%	63%	66%	69%	69%	77%	62%	62%	57%	65%	68%	67%	59%	66%	69%	60%	64%	84%	59%	70%	55%	56%
71.5%	77%	74%	80%	81%	73%	55%	65%	68%	72%	80%	66%	73%	73%	63%	76%	76%	72%	66%	70%	69%	72%
79.1%	90%	80%	84%	85%	86%	57%	82%	84%	85%	90%	74%	78%	82%	65%	90%	87%	89%	64%	73%	68%	68%
74.2%	87%	85%	83%	95%	73%	66%	81%	69%	68%	63%	77%	79%	68%	72%	71%	75%	68%	68%	70%	70%	71%
71.9%	76%	76%	83%	83%	85%	52%	60%	67%	70%	75%	74%	59%	72%	69%	79%	68%	78%	79%	69%	67%	69%
55.1%	60%	53%	55%	49%	48%	62%	47%	45%	49%	53%	62%	42%	51%	54%	55%	63%	67%	57%	64%	54%	67%
60.3%	57%	66%	56%	57%	62%	62%	66%	64%	64%	54%	56%	69%	60%	64%	57%	60%	57%	51%	77%	71%	37%
82.7%	86%	77%	88%	86%	82%	82%	77%	79%	79%	90%	88%	74%	83%	79%	83%	83%	86%	93%	66%	85%	90%
76.8%	75%	78%	82%	77%	73%	75%	83%	84%	77%	85%	78%	83%	72%	70%	80%	73%	73%	69%	70%	81%	74%
75.8%	75%	63%	82%	70%	79%	78%	87%	84%	78%	80%	87%	52%	81%	77%	88%	87%	79%	57%	55%	79%	74%
72.4%	77%	84%	77%	77%	62%	76%	71%	71%	72%	66%	68%	83%	72%	81%	60%	67%	83%	74%	83%	61%	56%
75.8%	89%	79%	79%	70%	83%	84%	69%	55%	70%	75%	75%	61%	77%	75%	86%	83%	75%	76%	76%	73%	82%
82.4%	89%	93%	96%	95%	82%	98%	89%	91%	93%	100%	85%	73%	88%	68%	94%	90%	61%	68%	91%	43%	43%
70.0%	75%	74%	80%	80%	71%	74%	74%	64%	68%	80%	71%	70%	74%	67%	80%	75%	69%	64%	68%	44%	49%
91.7%	98%	88%	99%	97%	93%	93%	88%	90%	90%	99%	99%	85%	94%	90%	96%	94%	97%	96%	77%	83%	79%
82.5%	90%	91%	91%	87%	81%	86%	88%	82%	76%	77%	87%	80%	88%	92%	83%	79%	86%	35%	85%	85%	83%
76.9%	79%	83%	77%	80%	71%	55%	80%	76%	68%	81%	82%	78%	77%	83%	81%	80%	82%	72%	80%	71%	79%
71.0%	68%	76%	79%	70%	67%	68%	65%	53%	61%	77%	76%	76%	67%	74%	81%	70%	73%	77%	67%	65%	81%

Model Similarity Dendrogram

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