	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	2nd 71.5%	8th 68.8%	9th 68.0%	1st 72.2%	6th 69.6%	21st 57.4%	13th 66.3%	4th 70.5%	11th 67.0%	3rd 71.3%	10th 67.4%	16th 62.3%	7th 69.3%	14th 65.1%	12th 66.9%	5th 70.0%	17th 61.9%	15th 63.3%	19th 60.1%	18th 60.6%	20th 58.7%
73.3%	77%	83%	81%	80%	75%	41%	77%	83%	80%	86%	80%	62%	80%	69%	83%	83%	58%	66%	58%	60%	77%
80.7%	82%	82%	81%	77%	78%	86%	80%	83%	73%	80%	91%	88%	84%	79%	82%	80%	91%	58%	85%	78%	77%
73.3%	72%	75%	84%	85%	69%	87%	75%	75%	75%	93%	75%	86%	75%	75%	0%	81%	75%	75%	67%	65%	75%
35.3%	43%	36%	33%	42%	30%	33%	38%	39%	41%	34%	39%	23%	43%	42%	29%	35%	31%	33%	40%	33%	24%
77.7%	84%	81%	84%	75%	84%	87%	66%	69%	78%	88%	84%	80%	88%	84%	78%	73%	68%	76%	82%	71%	52%
73.3%	77%	81%	73%	77%	76%	52%	80%	81%	73%	77%	67%	73%	81%	69%	75%	77%	75%	68%	67%	68%	73%
68.4%	71%	58%	71%	77%	75%	62%	72%	74%	74%	72%	71%	60%	71%	60%	76%	78%	62%	74%	62%	50%	67%
71.5%	95%	70%	70%	90%	85%	36%	70%	77%	76%	88%	65%	68%	74%	66%	90%	95%	57%	64%	51%	51%	63%
85.7%	81%	92%	88%	86%	93%	68%	80%	93%	82%	93%	94%	83%	89%	89%	85%	90%	88%	80%	76%	94%	76%
39.3%	42%	41%	36%	54%	54%	44%	32%	49%	48%	38%	43%	22%	49%	47%	38%	33%	33%	35%	36%	34%	18%
79.8%	86%	84%	68%	72%	89%	87%	70%	86%	81%	86%	76%	88%	89%	89%	72%	76%	78%	87%	83%	69%	59%
28.3%	37%	36%	27%	33%	41%	19%	28%	40%	24%	28%	35%	9%	34%	32%	32%	39%	23%	14%	26%	26%	12%
76.7%	68%	86%	81%	86%	73%	59%	77%	84%	79%	80%	76%	71%	77%	76%	78%	76%	75%	76%	72%	76%	84%
87.6%	96%	90%	85%	80%	89%	87%	90%	90%	86%	100%	85%	89%	93%	84%	83%	86%	91%	95%	82%	84%	75%
66.6%	70%	65%	78%	89%	63%	54%	79%	68%	75%	67%	58%	70%	76%	70%	67%	72%	58%	57%	57%	58%	47%
58.5%	69%	63%	65%	70%	66%	33%	45%	64%	58%	65%	52%	60%	57%	53%	67%	68%	51%	60%	50%	64%	48%
52.5%	52%	61%	60%	64%	60%	38%	44%	48%	54%	52%	54%	46%	43%	45%	66%	66%	41%	45%	46%	54%	64%
59.5%	71%	65%	70%	75%	61%	36%	59%	67%	62%	68%	56%	49%	62%	56%	70%	64%	46%	54%	47%	55%	57%
70.8%	75%	73%	74%	66%	49%	61%	77%	77%	71%	74%	72%	71%	72%	69%	69%	72%	82%	74%	77%	74%	58%
63.4%	70%	55%	62%	76%	75%	62%	67%	71%	66%	69%	61%	58%	68%	55%	67%	62%	59%	68%	56%	45%	59%
76.0%	78%	89%	80%	89%	80%	56%	90%	84%	78%	83%	79%	81%	79%	72%	70%	83%	64%	67%	59%	63%	71%
75.7%	78%	75%	83%	68%	83%	53%	81%	76%	82%	77%	72%	79%	84%	78%	81%	77%	77%	72%	69%	72%	72%
70.6%	94%	77%	83%	83%	74%	76%	65%	73%	65%	85%	83%	9%	59%	84%	81%	87%	46%	74%	72%	66%	47%
71.8%	69%	79%	74%	60%	72%	59%	72%	86%	77%	74%	77%	59%	76%	71%	76%	74%	71%	66%	68%	73%	75%
60.0%	63%	61%	62%	63%	62%	57%	63%	63%	57%	66%	63%	62%	63%	57%	60%	57%	60%	57%	59%	50%	54%
69.0%	71%	64%	57%	64%	69%	69%	60%	61%	65%	69%	74%	81%	66%	72%	60%	66%	76%	76%	80%	74%	75%
59.1%	72%	62%	70%	70%	65%	37%	54%	62%	60%	61%	50%	62%	64%	55%	69%	64%	57%	48%	44%	56%	59%
45.7%	52%	54%	45%	51%	71%	33%	51%	51%	48%	68%	40%	49%	55%	33%	63%	62%	33%	17%	33%	20%	30%
32.1%	33%	44%	29%	38%	39%	25%	33%	47%	29%	23%	59%	20%	32%	46%	35%	37%	25%	25%	28%	20%	7%
60.2%	72%	56%	56%	71%	57%	58%	48%	57%	57%	64%	64%	56%	58%	53%	62%	62%	67%	71%	64%	62%	49%
75.1%	87%	75%	79%	88%	81%	58%	82%	88%	75%	86%	71%	66%	78%	71%	88%	85%	63%	75%	56%	69%	56%
76.6%	79%	79%	70%	69%	85%	67%	79%	79%	79%	61%	79%	67%	79%	79%	79%	70%	79%	79%	87%	87%	76%
54.7%	50%	53%	61%	62%	48%	63%	53%	53%	53%	68%	53%	63%	53%	53%	58%	61%	53%	48%	46%	44%	53%
81.0%	88%	79%	80%	88%	85%	73%	83%	88%	79%	90%	78%	62%	83%	64%	91%	90%	85%	79%	68%	83%	85%
52.9%	71%	64%	64%	66%	26%	65%	40%	61%	57%	57%	52%	32%	63%	72%	0%	53%	51%	67%	67%	48%	34%
72.2%	80%	77%	71%	86%	87%	54%	82%	79%	78%	87%	82%	69%	76%	58%	82%	82%	57%	53%	49%	53%	75%
70.7%	83%	66%	72%	87%	63%	58%	76%	81%	66%	72%	70%	80%	76%	70%	69%	75%	65%	68%	60%	70%	57%
85.5%	82%	85%	78%	92%	83%	84%	91%	73%	86%	84%	85%	86%	89%	88%	83%	84%	99%	91%	82%	95%	76%
50.8%	63%	57%	46%	62%	61%	34%	62%	58%	50%	56%	45%	60%	58%	45%	64%	52%	43%	37%	35%	37%	41%
90.5%	89%	89%	98%	98%	82%	99%	89%	89%	89%	94%	89%	100%	89%	89%	100%	89%	89%	89%	80%	82%	89%
69.1%	71%	70%	67%	74%	100%	53%	78%	77%	81%	86%	63%	63%	71%	50%	70%	69%	45%	83%	43%	62%	75%
50.3%	55%	51%	46%	43%	56%	43%	49%	54%	45%	48%	54%	62%	57%	56%	54%	53%	43%	52%	46%	48%	41%
70.6%	75%	77%	80%	80%	77%	63%	64%	74%	67%	68%	82%	56%	67%	74%	74%	71%	71%	71%	68%	62%	61%

Model Similarity Dendrogram

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