DeepSeek-V4-Flash Enters Public Beta, Outperforming V4-Pro-Preview in Benchmarks
petrusenko_max · x · 2026-08-01
The DeepSeek-V4-Flash API is now available in public beta.
Key updates include:
- Benchmark Superiority: Surpasses the V4-Pro-Preview model, scoring 82.7 on Terminal Bench 2.1 and 76.7 on Cybergym.
- Native API Support: Natively supports the Responses API.
- Coding Optimization: Specifically optimized for Codex.
Related event: DeepSeek Launches V4-Flash, Outperforming Pro Preview(80 posts)→
More from Models
- Inkling-Small Local Test: Accurately Parses 85-Cell Medical Lab Reports on Mac — MaziyarPanahi · 2026-08-01
- Surge AI Releases High-Quality Datasets: Non-Coding Data Boosts Coding Benchmarks — echen · 2026-08-01
- OpenAI Price Cuts Unlock a New Class of Viable AI Products — JonathanRoss321 · 2026-08-01
- Gemini Accidentally Exposes Internal Reasoning: Caught Talking to Itself — MeltingEarbuds · 2026-08-01
- GPT-5.6 Excels at Code Maintenance While Claude Shines in Greenfield Coding — iskander · 2026-08-01
- Argmax Pro SDK 3 Brings Qwen3-ASR to iOS with Word-Level Timestamps — solyarisoftware · 2026-08-01