bruce on X: “Just completed GPU kernel bench, interesting reveals - DeepSeek v4.1 f…”

A fast, private reader for public X posts. No account, no tracking, no pop-ups.

PeekX is an independent tool and is not affiliated with, endorsed by or sponsored by X Corp. “X” and “Twitter” are trademarks of their respective owners. We only show posts that their authors made public and never access private or protected accounts. Downloaded media belongs to its creators — please respect their rights.

bruce on X: “Just completed GPU kernel bench, interesting reveals - DeepSeek v4.1 f…” | PeekX

Username or post link

Home / @bruce_x_offi / Post

Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)

@teortaxesTex

Oct 10

Depending on how you measure, Anthropic's models are *faster* than DeepSeek-Flash now. They have curiously long TTFT on API, though.
(I guess this is complete bullshit and they're doing screening/rewriting and then stream tokens with delay? Might also help them hide batching)

16 0 141

bruce

@bruce_x_offi

Replying to @teortaxesTex

Just completed GPU kernel bench, interesting reveals
- DeepSeek v4.1 flash > glm-5.3 flash
- DeepSeek v4.1 flash > haiku 5.5
- hy4 preview == gemini 3.8 flash
- Qwen 27B FP8 > Q4 Strata Next version @LottoLabs

Oct 10, 2026, 9:05 AM UTC

9 39

Download media

Every quality X serves, straight from X's media CDN. No watermark, no wait.

OriginalBEST

Photo · 1525×1659

Save & share

Turn this post into a clean image, or copy it as text or Markdown.

Open on X