Decision modelActive
pplx-decider-v1-27b
Perplexity
- Released
- -
- Data date
- October 3, 2026
pplx-decider-v1-27b is Perplexity’s 27-billion-parameter checkpoint for decisions over a state. The Decisions API accepts text, JSON, and images, then asks through a fixed schema for Choice, Noul, or Score. The result contains probabilities and confidence instead of a free-form answer.
It is based on Qwen3.8-27B. You can call the model through the Perplexity Decisions API or load its Apache-2.0 weights locally. The API limits a request to under 262,144 tokens including state, images, and questions. It costs $0.04 per 1M input tokens, with no output-token price or additional per-request fee.
Specifications and access
| Specification | Value and source |
|---|---|
| Model class | Multimodal decision model, not a text generatorSource |
| Output schema | Noul, Choice, and Score with probabilities and confidenceSource |
| Input | Text, JSON, and images as stateSource |
| Access | Perplexity Decisions API and local weightsSource |
| API model ID | pplx-decider-v1-27bSource |
| Checkpoint | perplexity-ai/pplx-decider-v1-27bSource |
| Base model | Qwen3.8-27BSource |
| API input limit | Under 262,144 tokens per request, including state, images, and questionsSource |
| License | Apache-2.0Source |
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
WinoGrande: accuracy (Show measurement, test conditions, and source)
- Source value
- 83.3
- Score
- 83.3
- Metric
- accuracy
- Unit
- %
- Category
- WinoGrande
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Perplexity Decider model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Perplexity API
FinancialPhraseBank: accuracy (Show measurement, test conditions, and source)
- Source value
- 84.18
- Score
- 84.18
- Metric
- accuracy
- Unit
- %
- Category
- FinancialPhraseBank
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Perplexity Decider model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Perplexity API
RAGTruth: accuracy (Show measurement, test conditions, and source)
- Source value
- 88.8
- Score
- 88.8
- Metric
- accuracy
- Unit
- %
- Category
- RAGTruth
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Perplexity Decider model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Perplexity API
JudgeBench: accuracy (Show measurement, test conditions, and source)
- Source value
- 78.29
- Score
- 78.29
- Metric
- accuracy
- Unit
- %
- Category
- JudgeBench
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Perplexity Decider model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Perplexity API
BBH: accuracy (Show measurement, test conditions, and source)
- Source value
- 82.8
- Score
- 82.8
- Metric
- accuracy
- Unit
- %
- Category
- BBH
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Perplexity Decider model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Perplexity API
JevBench public hard: accuracy (Show measurement, test conditions, and source)
- Source value
- 70.3
- Score
- 70.3
- Metric
- accuracy
- Unit
- %
- Category
- JevBench public hard
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Perplexity Decider model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Perplexity API
TabFact: accuracy (Show measurement, test conditions, and source)
- Source value
- 90.6
- Score
- 90.6
- Metric
- accuracy
- Unit
- %
- Category
- TabFact
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Perplexity Decider model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Perplexity API
ContractNLI: accuracy (Show measurement, test conditions, and source)
- Source value
- 80.78
- Score
- 80.78
- Metric
- accuracy
- Unit
- %
- Category
- ContractNLI
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Perplexity Decider model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Perplexity API
Circa: accuracy (Show measurement, test conditions, and source)
- Source value
- 89.2
- Score
- 89.2
- Metric
- accuracy
- Unit
- %
- Category
- Circa
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Perplexity Decider model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Perplexity API
Belebele: accuracy (Show measurement, test conditions, and source)
- Source value
- 94
- Score
- 94
- Metric
- accuracy
- Unit
- %
- Category
- Belebele
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Perplexity Decider model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Perplexity API
TruthfulQA binary: accuracy (Show measurement, test conditions, and source)
- Source value
- 85.4
- Score
- 85.4
- Metric
- accuracy
- Unit
- %
- Category
- TruthfulQA binary
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Perplexity Decider model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Perplexity API
Overall: Published aggregate (Show measurement, test conditions, and source)
- Source value
- 85.71
- Score
- 85.71
- Metric
- Published aggregate
- Unit
- %
- Category
- Overall
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Perplexity Decider model card
- Status
- disputed
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Perplexity API; weighting=Not disclosed in model card
- Context
- Perplexity publishes 85.71%; its aggregation or weighting is undisclosed and differs from the arithmetic mean of the eleven printed rows (84.33%). The aggregate is not recomputed.
Published prices
Prices apply to the stated unit. Resolution, output length, and provider can change the cost.
- API price
- $0.04 per 1M input tokens; output is free with no additional per-request feeSource
Sources and data date
Every statement links to its underlying documentation or leaderboard.
| Type | Evidence and data date |
|---|---|
| Research status | Research date October 4, 2026. 1 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Unresolved | published-overall-aggregation Original wording The published Overall is not the arithmetic mean of the printed rows; weighting or source correction remains undisclosed. |
| Additional source | Perplexity Decisions API (retrieved October 3, 2026) · Perplexity Decisions API quickstart · Editorial description reviewed October 3, 2026 |
| Additional source | pplx-decider model card (retrieved October 3, 2026; October 4, 2026) · pplx-decider model card · Editorial description reviewed October 3, 2026 |