aiaimodel.cards
← All benchmarks

τ3-Banking

Customer-service style tasks where the model uses tools and follows policies over a conversation with a simulated user.

  1. 1Muse Glimmer 30B · Meta
    23.5%

How each maker reported it

  • Muse Glimmer 30B Benchmarks

    Meta's own results. Muse Glimmer at high reasoning; Gemma4-31B and Qwen3.6-27B in thinking mode. GDPVal-AA v2 is an Elo-style score.

Only each model's own maker's number is shown; scores a maker reports for rival models are left out.