Beam 1.0 ranks #1 among US open-weight models on Excel financial modeling benchmark EMB
bigblueboo · x · 2026-10-21
Per Vals AI, Beam 1.0 performed especially well on EMB, a benchmark testing agents on building Excel financial models: #14 among all open-weight models and #1 among US open-weight models, just ahead of Muse Spark Open.
More from Models
- Humansand launches Ampersand, a collaborator model that beats frontier models in multi-month simulations — niloofar_mire · 2026-10-21
- AutoResearchExam adds Gemini 4 Argon: frontier ML-research performance at 1/3 the cost — AlexGDimakis · 2026-10-21
- Gemini 4 Argon matches frontier ML-engineering performance at 2-3x lower cost on AutoResearchExam — AlexGDimakis · 2026-10-21
- Chinese AI Twitter Goes Viral Parsing Zhipu, Kimi, DeepSeek's Open-Source Playbooks — teortaxesTex · 2026-10-21
- Testing 41 shades of blue on AI agents: they really do prefer some colors over others — danshipper · 2026-10-21
- Persimmon Launches Amp, an Agent Model Trained in Months-Long Simulations — Diyi_Yang · 2026-10-21