ELSEIF
Your brief EB
444 stories from 137 feeds 657 clusters Refreshed 12 minutes ago next pull 13:24

PERFORMANCE Signal 471

Qwen3.8-Flash-Next ranks fourth in intelligence among 110 models with 180B total and 6B active parameters

Artificial Analysis benchmarks place Alibaba's open-weights Qwen3.8-Flash-Next at rank four in intelligence and above average in speed among 110 comparable models, while flagging extreme verbosity and unresolved pricing.

WHY IT MATTERS

For teams evaluating open-weights LLMs, the 6B active parameters per token on a 180B total model suggest strong inference economics if the listed $0.00 pricing holds. The 200M token verbosity during benchmarking signals that production cost and latency could be higher than raw speed metrics imply, since the model generates nearly twice the median token volume per task.

Written by elseif from the cluster below · every claim links back to a source

The three things worth knowing

01

Qwen3.8-Flash-Next scores 56 on the Artificial Analysis Intelligence Index, ranking fourth out of 110 models and well above the median of 28.

02

The model outputs 73.5 tokens per second, faster than the median of 65, but generated 200M tokens during evaluation versus a median of 110M.

03

Pricing is listed as $0.00 per 1M tokens for both input and output, though the cost-per-task metric is marked N/A.

THE CLUSTER

Same story, 1 feed.

ORDERED BY FIRST SEEN
artificialanalysis.ai via Hacker News Qwen3.8-Flash-Next Intelligence, Performance and Price Analysis Open ↗