Groq

qwen3.6-27b

Made by Alibaba. Released 2026-04-22. Accessibility not recorded. Cheapest standard rate we hold: $3 per million output tokens, no context split.

What it costs

TierKindInOutCached inFrom
standardtext$0.60$3$0.30registry

per million tokens, US dollars. * marks a rate from a single registry or two that disagree — the best available number rather than a confirmed one. Every other row is confirmed against a seller or a licensed index.

What it scores, by house

BenchmarkHouseScoreEvaluatedScaffold
chess puzzlesEpoch AI0.1±0.032026-08-07none
chess puzzlesEpoch AI0.2±0.042026-08-07
frontiermath tiers 1 3 v2Epoch AI0.3±0.032026-08-29none
frontiermath tiers 1 3 v2Epoch AI0.4±0.032026-08-28
gpqa diamondEpoch AI0.9±0.022026-08-07
gpqa diamondEpoch AI0.8±0.032026-08-07none
mystery game puzzlesEpoch AI0.1±0.032026-08-27none
otis mock aime 2024 2025near its ceilingEpoch AI0.7±0.072026-08-07none
otis mock aime 2024 2025near its ceilingEpoch AI0.9±0.042026-08-07
critptcollected by Epoch AI0.0none
dtbenchnear its ceilingcollected by Epoch AI0.8
lmcacollected by Epoch AI34.5
scicodecollected by Epoch AI0.4none

These scores are not comparable between houses and are not added up. A score is dated by when it was evaluated, not when the model was released, and a score without its scaffold is not a measurement — which is why both are printed.

Every rate we hold · Why there is no single best model · Everything from Groq