AMD MI355X beats Nvidia on inference margins in SemiAnalysis InferenceX benchmark
AccBalanced · x · 2026-10-05
SemiAnalysis's open-source InferenceX agentic benchmark shows AMD MI355X posting the best margins on several open models: Kimi K3 45.7% vs 43.8% (GB300), GLM 5.3 63.4% vs 63.2% (GB200), MiniMax M3 51.5% vs 48.4% (B300), DeepSeek V4 Pro 87.9%. Every datapoint is produced by public GitHub Actions runs with open recipes and weekly auditable DB snapshots, adding 1,000+ datapoints weekly across TPU, GB300, MI355X and more.
More from Infra
- Microsoft AI CEO Suleyman: $100B training runs are coming — rohanpaul_ai · 2026-10-05
- Inference Economics: Google Now Processes 3.2 Quadrillion Tokens Monthly, 7x a Year Ago — mikeflache · 2026-10-05
- InP choke pushes industry toward 1um lasers on GaAs and hollow-core fiber — jwt0625 · 2026-10-05
- Cloudflare's new Web Search API is just a wrapper around Exa and a few other providers — gaganghotra_ · 2026-10-05
- Top 10 providers on OpenRouter ranked by monthly token volume — stuffyokodraws · 2026-10-05
- Crusoe CEO explains its layered compute business: 5-year leases to high-margin inference — AccBalanced · 2026-10-05