	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	3rd 67.1%	8th 65.9%	5th 66.8%	1st 67.7%	19th 60.1%	18th 60.7%	4th 66.8%	9th 64.5%	10th 64.4%	2nd 67.5%	12th 63.8%	20th 59.7%	11th 64.2%	17th 61.3%	6th 66.7%	7th 66.7%	16th 63.1%	14th 63.5%	21st 57.5%	15th 63.2%	13th 63.7%
67.0%	68%	68%	68%	68%	52%	68%	74%	65%	64%	77%	64%	68%	68%	61%	74%	61%	68%	54%	61%	80%	77%
32.2%	28%	36%	25%	25%	8%	58%	24%	46%	36%	28%	31%	28%	25%	78%	36%	25%	25%	30%	31%	28%	25%
80.2%	83%	83%	85%	80%	80%	80%	85%	80%	75%	83%	80%	71%	80%	89%	83%	83%	83%	80%	61%	80%	80%
61.8%	64%	55%	64%	64%	55%	55%	65%	71%	71%	64%	55%	55%	55%	71%	65%	65%	71%	68%	55%	55%	55%
91.0%	96%	87%	100%	89%	87%	87%	100%	81%	100%	100%	87%	87%	87%	87%	100%	89%	100%	87%	87%	87%	87%
78.9%	70%	70%	70%	70%	61%	100%	89%	81%	89%	76%	89%	77%	76%	86%	76%	76%	89%	78%	76%	76%	81%
44.6%	54%	51%	51%	49%	37%	32%	44%	55%	55%	44%	40%	32%	40%	32%	46%	54%	49%	56%	32%	42%	42%
49.2%	54%	54%	61%	70%	40%	42%	42%	58%	48%	54%	42%	51%	42%	37%	62%	56%	42%	49%	42%	45%	42%
58.8%	55%	55%	59%	58%	67%	61%	67%	59%	58%	67%	59%	58%	58%	55%	49%	50%	55%	58%	59%	58%	70%
57.4%	55%	80%	61%	72%	55%	55%	46%	46%	51%	61%	55%	66%	65%	55%	64%	51%	51%	52%	55%	55%	55%
52.3%	64%	52%	56%	49%	41%	41%	72%	41%	53%	49%	52%	64%	41%	38%	60%	75%	41%	59%	41%	64%	45%
71.4%	70%	75%	71%	71%	80%	56%	75%	71%	71%	75%	80%	80%	65%	75%	69%	65%	63%	62%	71%	75%	80%
76.6%	74%	74%	72%	74%	74%	86%	100%	74%	74%	74%	74%	75%	74%	74%	74%	74%	86%	79%	74%	74%	74%
43.2%	48%	48%	48%	48%	34%	56%	46%	47%	46%	49%	48%	32%	48%	32%	43%	46%	28%	40%	32%	34%	54%
50.4%	55%	55%	55%	55%	55%	46%	61%	45%	41%	51%	55%	55%	55%	55%	51%	51%	51%	37%	55%	37%	37%
54.0%	63%	55%	55%	55%	55%	55%	56%	48%	48%	55%	55%	51%	56%	48%	58%	51%	48%	48%	56%	64%	55%
71.1%	75%	76%	75%	75%	60%	54%	76%	41%	76%	76%	76%	67%	64%	64%	71%	75%	76%	77%	76%	75%	89%
67.9%	65%	71%	75%	75%	64%	75%	70%	65%	61%	70%	65%	68%	77%	56%	67%	75%	75%	62%	58%	75%	56%
52.9%	58%	53%	45%	50%	48%	48%	64%	57%	56%	70%	34%	39%	75%	49%	52%	65%	47%	46%	45%	75%	35%
61.4%	70%	70%	66%	75%	49%	49%	70%	64%	64%	58%	57%	78%	64%	58%	69%	59%	64%	57%	35%	49%	64%
71.6%	70%	75%	69%	70%	64%	72%	75%	80%	74%	70%	75%	72%	70%	71%	59%	64%	75%	78%	87%	69%	64%
67.0%	67%	64%	64%	67%	64%	75%	67%	72%	75%	67%	64%	64%	75%	64%	67%	75%	64%	69%	64%	64%	54%
44.9%	44%	45%	45%	44%	35%	48%	51%	48%	52%	48%	48%	37%	35%	54%	44%	54%	41%	31%	43%	59%	37%
74.7%	74%	86%	89%	74%	74%	75%	74%	75%	74%	74%	74%	74%	74%	74%	72%	74%	74%	62%	74%	74%	74%
46.7%	58%	58%	51%	58%	34%	32%	61%	58%	51%	48%	40%	39%	45%	34%	47%	53%	47%	40%	39%	34%	54%
69.6%	71%	70%	72%	87%	77%	68%	61%	65%	65%	100%	77%	68%	72%	54%	69%	83%	61%	54%	51%	70%	67%
56.5%	56%	51%	56%	56%	56%	56%	51%	56%	64%	56%	41%	50%	54%	54%	56%	55%	76%	75%	62%	51%	54%
65.4%	64%	64%	70%	70%	100%	55%	64%	71%	65%	80%	69%	35%	69%	34%	74%	71%	64%	58%	64%	64%	69%
56.8%	75%	71%	75%	75%	64%	45%	64%	54%	54%	46%	37%	37%	37%	54%	75%	60%	46%	46%	47%	66%	64%
79.0%	69%	88%	75%	69%	65%	94%	76%	75%	75%	88%	100%	75%	88%	100%	75%	74%	71%	100%	51%	75%	75%
66.6%	66%	56%	66%	66%	67%	88%	66%	66%	66%	66%	66%	66%	66%	66%	66%	65%	66%	67%	66%	66%	66%
67.3%	65%	65%	71%	71%	81%	50%	61%	72%	71%	65%	65%	61%	71%	61%	65%	65%	65%	81%	61%	81%	65%
67.1%	68%	67%	68%	68%	68%	50%	68%	64%	63%	68%	68%	87%	68%	77%	68%	68%	68%	68%	50%	68%	68%
57.0%	69%	55%	55%	67%	59%	49%	49%	67%	63%	55%	49%	49%	49%	55%	67%	70%	67%	63%	32%	49%	60%
68.6%	90%	65%	89%	86%	40%	56%	54%	89%	41%	72%	54%	40%	72%	68%	100%	81%	69%	73%	69%	58%	75%
66.6%	72%	75%	66%	70%	24%	61%	65%	65%	60%	86%	74%	81%	75%	47%	66%	66%	75%	60%	68%	71%	72%
68.8%	76%	66%	65%	78%	66%	66%	78%	63%	74%	78%	66%	66%	78%	72%	58%	78%	56%	66%	62%	66%	66%
86.4%	87%	87%	87%	87%	87%	87%	87%	89%	87%	87%	87%	84%	87%	87%	90%	93%	76%	95%	87%	75%	81%
57.7%	63%	54%	63%	63%	81%	54%	63%	59%	51%	71%	63%	34%	66%	35%	66%	63%	59%	59%	45%	45%	54%
88.2%	90%	90%	100%	100%	80%	81%	100%	100%	100%	90%	80%	80%	80%	80%	90%	90%	90%	81%	80%	81%	90%
51.2%	55%	48%	56%	55%	61%	29%	72%	56%	65%	56%	65%	41%	51%	29%	56%	62%	51%	56%	21%	35%	56%
82.8%	94%	94%	86%	86%	83%	53%	83%	86%	83%	83%	94%	53%	86%	94%	94%	84%	70%	94%	75%	81%	83%
70.7%	72%	72%	72%	72%	51%	61%	58%	47%	61%	66%	89%	72%	76%	70%	75%	72%	72%	76%	72%	89%	89%

Model Similarity Dendrogram

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