Compare two models

Mean overlap between two models' lists across every list both answered · 100 means identical · Color runs from 61 (lightest) to 82 (darkest) · Select a cell to compare that pair

	Claude Opus 5.5	GPT-6.1 Sol	Gemini 4 Argon	Qwen 3.8 Max	DeepSeek V4 Pro	GLM-5.3	Kimi K3	MiniMax M3	Mistral Large 4	Nemotron 3 Ultra
Claude Opus 5.5		82	77	77	71	75	74	67	67	69
GPT-6.1 Sol	82		76	76	69	73	70	63	65	65
Gemini 4 Argon	77	76		74	68	71	70	61	64	65
Qwen 3.8 Max	77	76	74		69	73	73	68	67	68
DeepSeek V4 Pro	71	69	68	69		71	73	65	72	67
GLM-5.3	75	73	71	73	71		75	67	69	71
Kimi K3	74	70	70	73	73	75		64	71	70
MiniMax M3	67	63	61	68	65	67	64		64	66
Mistral Large 4	67	65	64	67	72	69	71	64		70
Nemotron 3 Ultra	69	65	65	68	67	71	70	66	70