Beam 1.0 tops Vals AI private eval as #1 US open-weight model, ranks #14 globally
bigblueboo · x · 2026-10-21
Vals AI results show Beam 1.0 is now the top US open-weight model, just ahead of Muse Spark Open, and ahead of Mistral Large 4 and Inkling. Globally it ranks #14 among all open-weight models.
Beam did especially well on EMB, which tests agents on building Excel financial models. The eval is private, so it can't easily be gamed.
Related event: Beam 1.0 Tops US Open-Weight Models in Vals AI Rankings(2 posts)→
More from Models
- One Week After Gemini 4 Argon Launch, Users Are Building 3D Worlds, Physics Sims and Games — minchoi · 2026-10-21
- Minimax H3 local workflow is '0/10': hyper-sensitive prompts and VRAM failures on 24GB — Ambitious_Corgi5723 · 2026-10-21
- ChatGPT's new UI keeps attaching wrong photos to real people, user reports — ProfessionalAd1198 · 2026-10-21
- Tone-filtering AI is "preemptive shame applied at machine speed" — PierceLilholt · 2026-10-21
- Was Opus quietly nerfed? Same prompt, 20 days apart, noticeably worse output — JiliJeanlouis · 2026-10-21
- Users hit a new Claude friction: paternalistic redaction of 'sensitive' data, no explanation — mattbeane · 2026-10-21