Beam Token Breakdown: Only 26% of Its 26k Output Tokens per Task Are Answers
ArtificialAnlys · x · 2026-10-16
Artificial Analysis breaks down Beam's token usage: 26k output tokens per Intelligence Index task, of which 19k go to reasoning and 7k to answers — only 26% of output is final answers, the 28th-lowest share among 219 models tested on Intelligence Index v4.3.
This underpins its Cyber Index lead among US open weights models being driven by token efficiency; the accompanying chart plots models on Intelligence Index score vs output tokens per task, with Beam in the efficient quadrant.
More from Models
- Opus 5.5 still leads a month later, but open-weight decision models are closing in — airesearch12 · 2026-10-16
- Google restricts Gemini Pro access for Google Plus subscribers, matching free tier — EmergencyLess8861 · 2026-10-16
- Meta releases Muse Spark Open, trained with vLLM-powered RL inference from day one — colinmcnamara · 2026-10-16
- Meta open-sources Muse Spark: runs on two Mac Studios, license bans passing output off as human-written — mawcopolow · 2026-10-16
- Golden Gate Claude explainer resurfaces: interpretability premise still holds — HarperSCarroll · 2026-10-16
- Hugging Face livestreams release of a new open-weight model — huggingface · 2026-10-16