Ling-3.0-flash-Fin: 124B param model fixes context drift in finance workflows
FellMentKE · x · 2026-08-28
Ling-3.0-flash-Fin is a finance-enhanced version of the Ling-3.0-flash model, designed to address context drift when processing long reports and workbooks. With 124B total and 5.1B active parameters, it maintains definitions, sources, and calculations across documents. The model achieved competitive results on benchmarks like FinFIRST, FinCRAFT, and SpreadsheetBench. It is available for free for one month via OpenRouter, with open-source weights release planned for next week.
More from Models
- Intrinsic Discovery method enables unsupervised model exploration — burny_tech · 2026-08-28
- Ambi releases CARGO physical AI model with 72.5% stacking density — jfiance · 2026-08-28
- MiniMax-H3 on 8×H200: 1.95× Lossless Speedup, Up to 6.24× — ying11231 · 2026-08-28
- Deep Dive: Engram Enables Smaller Models to Reason Like Giants by Decoupling Memory — chocolateUI · 2026-08-28
- Domingos: AI is the leakiest abstraction yet, and what leaks is the LLM mess — pmddomingos · 2026-08-28
- Grok-4.6 Ranks #15 in Agent Arena with 13% Success Rate Boost — arena · 2026-08-28