Ant Group releases Ling-3.0-flash-Fin, an open-weights AI model for finance

Artificial Analysis reports that the model matches MiniMax-M2.7’s Intelligence Index score of 23 with roughly half the active parameters per token: 5.1 billion versus 10 billion.

1 Source, 35d ago, first seen 35d ago

TLDR

Artificial Analysis reports that Ant Group released Ling-3.0-flash-Fin, a text-only, open-weights model built on Ling-3.0-flash. Ant Group says it developed the model with financial institutions and industry experts to support financial research, including checking sources, building valuation spreadsheets and writing reports.

Artificial Analysis gives it 24 on its Finance & Accounting Index, matching Ling-3.0-flash-VL. It reports higher business knowledge accuracy for Fin than VL—17% versus 11%—but also higher business knowledge hallucination: 33% versus 19%.

The evaluator notes that Fin uses 5.1 billion active parameters per token but has 124 billion total parameters.

Today's Rank

—

Not ranked yet

Combined views

—

1 Source, first seen 35d ago

1 Source

@ArtificialAnlysLing-3.0-flash-Fin sits on the Intelligence Index vs. active parameters Pareto frontier, scoring 23 with 5.1B active parameters per token vs. a score of 25 or Ling-3.0-flash-VL which uses 5.5B active per token. Both have 124B total parameters, while Qwen3.8 27B (xhigh) scores 34 with 27B total parameters, placing both Ling models below the total-parameter frontier.35d

Today's Rank

—

Not ranked yet

Combined views

—

1 Source, first seen 35d ago

— likes

Today's Rank

—

Not ranked yet

Today's Rank

—

Not ranked yet

— likes

— comments

— saves

— reposts

— comments

— saves

— reposts

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

1 Source

@ArtificialAnlysLing-3.0-flash-Fin sits on the Intelligence Index vs. active parameters Pareto frontier, scoring 23 with 5.1B active parameters per token vs. a score of 25 or Ling-3.0-flash-VL which uses 5.5B active per token. Both have 124B total parameters, while Qwen3.8 27B (xhigh) scores 34 with 27B total parameters, placing both Ling models below the total-parameter frontier.35d

1 Source

@ArtificialAnlysLing-3.0-flash-Fin sits on the Intelligence Index vs. active parameters Pareto frontier, scoring 23 with 5.1B active parameters per token vs. a score of 25 or Ling-3.0-flash-VL which uses 5.5B active per token. Both have 124B total parameters, while Qwen3.8 27B (xhigh) scores 34 with 27B total parameters, placing both Ling models below the total-parameter frontier.35d

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

1 Source

@ArtificialAnlysLing-3.0-flash-Fin sits on the Intelligence Index vs. active parameters Pareto frontier, scoring 23 with 5.1B active parameters per token vs. a score of 25 or Ling-3.0-flash-VL which uses 5.5B active per token. Both have 124B total parameters, while Qwen3.8 27B (xhigh) scores 34 with 27B total parameters, placing both Ling models below the total-parameter frontier.35d