Qwen·#38 of 276 on the current board·cheaper than #35 GPT-5.4 Mini
Qwen3.8 27B is a language model from Qwen. It ranks #38 of 276 on ModelCap's current board, with an Index score of 68.4, measured on 4 public benchmarks. Its score range of 62.4–74.4 spans positions #26–#59. It is listed at $0.42 per million input tokens and $3.00 per million output tokens across 16 providers. It reads up to 1M tokens of context, and its weights are openly downloadable.
Figures as of 28 Sept 2026, 18:11 UTC · download the public dataset · methodology
Provider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.
Structured rows reported in this exact model repository at the pinned revision below. They are the publisher talking about itself: never measured evidence, never a score input on their own. They remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.
BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.
These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.
The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.
Not yet published: the base model it derives from, pinned evaluation dataset versions.
A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.
Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.
OpenRouter weekly popularity across the full model catalogue.
Independent providers versus the model's open or closed cohort, weighted by uptime.
Hugging Face 30-day downloads for open models; neutral for closed models.
Time since first public availability, on a six-month half-life.
qwen/qwen3.8-27bOpen weights. Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI.
Models within 3 places of #38 on the ModelCap Index.
Index score within 3 points of, or above, this model's, with a lower listed blended price (3:1 input:output).
The same publisher's other current models with a public Index position.
Qwen3.8 27B holds ModelCap Index position #38 of 276 ranked language models as of 28 September 2026, with an Index score of 68.4 (interval 62.4–74.4); evidence: measured. The Index combines public benchmark boards with published uncertainty; the methodology page explains the weighting.
Qwen3.8 27B is listed at $0.42 per 1M input tokens and $3.00 per 1M output tokens as of 28 September 2026; the lowest output price among 16 providers is $1.88 on DeepInfra. Prices come from the OpenRouter catalogue and re-observe on every refresh; at least one provider lists a free tier. For 1,000 requests using 2,000 input and 500 output tokens each, the listed rates imply $2.34 total (2M input + 0.5M output). This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the chosen endpoint's rate and limits before budgeting.
Qwen3.8 27B has a published context window of 1M tokens (1,000,000) and a maximum output of 131K tokens. Individual providers can serve less than the published maximum; the providers table lists each endpoint's own limit.
Open weights (apache-2.0). Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI. The repository is Qwen/Qwen3.8-27B on Hugging Face.
16 providers serve Qwen3.8 27B through OpenRouter as of 28 September 2026: Darkbloom, Wafer, Reka, DekaLLM, Ionstream and DeepInfra and 10 more. Each provider's price, context limit, quantization and measured uptime are in the providers table above.
Qwen3.8 27B has published results on 4 public boards tracked by ModelCap as of 28 September 2026: Arena coding 1504 (#65 of 404), AA Intelligence Index 33.7 (#75 of 173), AA Humanity's Last Exam 33.9% (#106 of 633) and WildClawBench OpenClaw 48.0 (#15 of 34). Each board page ranks every tracked model on that benchmark. The ModelCap Index scores the results its methodology admits, with published uncertainty, and shows reference boards without scoring them.
Qwen3.8 27B ranks #38 (Index 68.4) and Qwen3.5 397B A17B ranks #42 (Index 67.2) on the ModelCap Index as of 28 September 2026. The head-to-head page lines up their benchmarks, listed prices, context windows and provider counts side by side.
Qwen3.8 27B first appeared in the catalogue on 14 Aug 2026. It is the current version in its family. Rank and price movements since then are recorded on the site's changes feed.