Matching posts

Matching terms are highlighted

Code2Video-AA: DeepSeek V4.1 Flash tops open-weight models at 1053 Elo

Artificial Analysis benchmarked code-generated brand videos on 114 tasks; Opus 5.5 leads at 1536 Elo while V4.1 Flash is the best open-weight model at 1053.

deepseek-v4.1@lujunneng　Filed in No.020

1 day agoCopy original

POST

DeepSeek open-sources DeepInfer inference engine, limited to V4.1 Flash and datacenter GPUs

聊一聊Deepseek开源的推理引擎DeepInfer 先说结论, 这次开源主要利好对托管厂商, 对生态开放最新推理工程实…

deepseek-v4.1@Taylor_AIPM　Filed in No.020

15 hours agoCopy original

POST

Matthew Berman calls DeepSeek V4.1 Flash the best open-weights model

A one-line verdict that DeepSeek V4.1 Flash is currently the best open-weights model, with no test details or numbers given.

deepseek-v4.1@MatthewBerman　Filed in No.020

1 day agoCopy original

POST

Artificial Analysis Intelligence Index v5: Kimi K3.1 Pro leads open weights at 46, DeepSeek V4.1 Flash at 32

The post details v5 changes: 60% private datasets to cut contamination plus new FrontierCode 2.0 and Terminal-Bench-Science tests, with Kimi K3.1 Pro at 46 and DeepSeek V4.1 Flash tied with GLM-5.3 at 32 among open weights.

deepseek-v4.1@0xsidzsh　Filed in No.020

15 hours agoCopy original

POST

DeepSeek V4.1 Flash open weights and MIT license prompt debate on closed models

Using a $2 Blender render as a hook, the post notes V4.1 Flash ships open weights under MIT at the same low price with better reasoning, coding and agents, and asks whether open weights are now the default.

deepseek-v4.1@0xDrexo　Filed in No.020

19 hours agoCopy original

Space Bunny (anonymous M3.1 Flash) ranks #2 among open-weight models on RSI-Inference Bench

The independent RSI-Inference Bench places Space Bunny second among open-weight models behind DeepSeek V4.1 Flash, and first among open models on its inference optimization track at 1.26x.

minimax-m3.1@onloglogn　Filed in No.021

1 day agoCopy original

POST

User calls DeepSeek V4.1 Flash the best open model right now

A user says DeepSeek V4.1 Flash 1017 is the best open model available, especially given its relatively friendly size, and is now waiting for the next GLM.

deepseek-v4.1@MiaAI_lab　Filed in No.020

19 hours agoCopy original

Hands-on: MiniMax M3.1 Flash codes an open-world FPS game over long sessions

The author ran M3.1 Flash via API in DeepSeek Harness and mcode over long sessions, adding features one by one to build a code-only open-world FPS with no external assets, calling it a big step up from M3 and planning to spend the rest of the month's quota improving it.

minimax-m3.1@ItsmeAjayKV　Filed in No.021

1 day agoCopy original

POST

User: DeepSeek V4.1 Flash still best open model at its size for overnight agent loops

A brief usage report says deepseek-v4.1-flash-1017 remains the strongest open model at its size for agent loops running overnight.

deepseek-v4.1@HiLinkup_AI　Filed in No.020

14 hours agoCopy original

Mollick: open-weight gap widens on new eval, DeepSeek V4.1 Flash scores 32

…组数据衡量的是该评测下的能力，成本、部署自由度和具体任务表现仍需分别比较。 #AI #大模型 #开源模型

deepseek-v4.1@0xlunasterling　Filed in No.020

14 hours agoCopy original

Showing10of60posts

10 per batch

Keep scrolling to reveal posts 11–20

Showing the first 60 matches. Narrow the query with a model name or tag to find more specific results.