Decision modelActive
Clef-Flash
Cloudflare
- Released
- October 1, 2026
- Data date
- October 3, 2026
Clef-Flash is Cloudflare’s smaller variant with 9 billion parameters. Like Clef, it evaluates supplied state through typed questions and returns Choice, Noul, and Score as probabilities. It does not generate an explanation. Text, JSON, images, and video remain supported inputs.
Qwen3.5-9B and a vision encoder form its base. Cloudflare specifies a 64k-token context. It is available through Workers AI as @cf/cloudflare/clef-flash for $0.09 per 1M input tokens, as well as a local Apache-2.0 checkpoint. The free neuron allowance is shared across the account. Its smaller design targets a faster structured readout, not a chat dialogue.
Specifications and access
| Specification | Value and source |
|---|---|
| Model class | Multimodal System One decision model, not a chat modelSource |
| Output schema | Choice, Noul and Score with probabilities, without free-form answer textSource |
| Input | Text, JSON, images, and videoSource |
| Access | Workers AI API and local weightsSource |
| API model ID | Workers AI: @cf/cloudflare/clef-flashSource |
| Checkpoint | Cloudflare/clef-flashSource |
| Base model | Qwen/Qwen3.5-9B with vision encoderSource |
| Context window | 64k tokens (provider specification)Source |
| License | Apache-2.0Source |
Page 1 of 4
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.
Decision Index 0.2.1: BFCL (case exact accuracy) (Show measurement, test conditions, and source)
- Source value
- 98.8
- Score
- 98.8
- Metric
- BFCL (case exact accuracy)
- Unit
- %
- Benchmark version
- 0.2.1
- Category
- Decision Index 0.2.1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cloudflare Clef Flash model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Cloudflare internal evaluation; Benchmark version=0.2.1; Request latency=no
Decision Index 0.2.1: ToolRet (nDCG@10) (Show measurement, test conditions, and source)
- Source value
- 66.4
- Score
- 66.4
- Metric
- ToolRet (nDCG@10)
- Unit
- %
- Benchmark version
- 0.2.1
- Category
- Decision Index 0.2.1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cloudflare Clef Flash model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Cloudflare internal evaluation; Benchmark version=0.2.1; Request latency=no
Decision Index 0.2.1: API-Bank (accuracy) (Show measurement, test conditions, and source)
- Source value
- 93.1
- Score
- 93.1
- Metric
- API-Bank (accuracy)
- Unit
- %
- Benchmark version
- 0.2.1
- Category
- Decision Index 0.2.1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cloudflare Clef Flash model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Cloudflare internal evaluation; Benchmark version=0.2.1; Request latency=no
Decision Index 0.2.1: BANKING77 (macro-F1) (Show measurement, test conditions, and source)
- Source value
- 90.9
- Score
- 90.9
- Metric
- BANKING77 (macro-F1)
- Unit
- %
- Benchmark version
- 0.2.1
- Category
- Decision Index 0.2.1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cloudflare Clef Flash model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Cloudflare internal evaluation; Benchmark version=0.2.1; Request latency=no
Decision Index 0.2.1: CLINC150+OOS (macro-F1) (Show measurement, test conditions, and source)
- Source value
- 66.8
- Score
- 66.8
- Metric
- CLINC150+OOS (macro-F1)
- Unit
- %
- Benchmark version
- 0.2.1
- Category
- Decision Index 0.2.1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cloudflare Clef Flash model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Cloudflare internal evaluation; Benchmark version=0.2.1; Request latency=no
Decision Index 0.2.1: RouterBench (selected quality) (Show measurement, test conditions, and source)
- Source value
- 79.9
- Score
- 79.9
- Metric
- RouterBench (selected quality)
- Unit
- %
- Benchmark version
- 0.2.1
- Category
- Decision Index 0.2.1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cloudflare Clef Flash model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Cloudflare internal evaluation; Benchmark version=0.2.1; Request latency=no
Decision Index 0.2.1: Home appliance simulator (case exact accuracy) (Show measurement, test conditions, and source)
- Source value
- 97.7
- Score
- 97.7
- Metric
- Home appliance simulator (case exact accuracy)
- Unit
- %
- Benchmark version
- 0.2.1
- Category
- Decision Index 0.2.1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cloudflare Clef Flash model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Cloudflare internal evaluation; Benchmark version=0.2.1; Request latency=no
Decision Index 0.2.1: SGD/SGD-X (macro-F1) (Show measurement, test conditions, and source)
- Source value
- 34.2
- Score
- 34.2
- Metric
- SGD/SGD-X (macro-F1)
- Unit
- %
- Benchmark version
- 0.2.1
- Category
- Decision Index 0.2.1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cloudflare Clef Flash model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Cloudflare internal evaluation; Benchmark version=0.2.1; Request latency=no
Decision Index 0.2.1: ContractNLI (macro-F1) (Show measurement, test conditions, and source)
- Source value
- 84.3
- Score
- 84.3
- Metric
- ContractNLI (macro-F1)
- Unit
- %
- Benchmark version
- 0.2.1
- Category
- Decision Index 0.2.1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cloudflare Clef Flash model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Cloudflare internal evaluation; Benchmark version=0.2.1; Request latency=no
Decision Index 0.2.1: ANLI (macro-F1) (Show measurement, test conditions, and source)
- Source value
- 59.1
- Score
- 59.1
- Metric
- ANLI (macro-F1)
- Unit
- %
- Benchmark version
- 0.2.1
- Category
- Decision Index 0.2.1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cloudflare Clef Flash model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Cloudflare internal evaluation; Benchmark version=0.2.1; Request latency=no
Decision Index 0.2.1: BPoMP (accuracy) (Show measurement, test conditions, and source)
- Source value
- 95.4
- Score
- 95.4
- Metric
- BPoMP (accuracy)
- Unit
- %
- Benchmark version
- 0.2.1
- Category
- Decision Index 0.2.1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cloudflare Clef Flash model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Cloudflare internal evaluation; Benchmark version=0.2.1; Request latency=no
Decision Index 0.2.1: Humicroedit (accuracy) (Show measurement, test conditions, and source)
- Source value
- 75.1
- Score
- 75.1
- Metric
- Humicroedit (accuracy)
- Unit
- %
- Benchmark version
- 0.2.1
- Category
- Decision Index 0.2.1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cloudflare Clef Flash model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Run=Cloudflare internal evaluation; Benchmark version=0.2.1; Request latency=no
Page 1 of 4
Published prices
Prices apply to the stated unit. Resolution, output length, and provider can change the cost.
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 | forecastbench-scale Original wording ForecastBench prints Brier values 13.9 and 10.6 without a stated scale; the raw values remain unchanged and are not divided by 100. |
| Additional source | Cloudflare announcement (retrieved October 3, 2026) · Cloudflare Clef announcement · Editorial description reviewed October 3, 2026 |
| Additional source | Clef-Flash model card (retrieved October 3, 2026; October 4, 2026) · Clef-Flash model card · Editorial description reviewed October 3, 2026 |
| Additional source | Workers AI pricing (retrieved October 3, 2026) · Workers AI pricing · Editorial description reviewed October 3, 2026 |