Clef and Clef-Flash released
Cloudflare · Model release
Source confirmed
Data as of October 8, 2026 · How the score is built
CurrentOpen WeightNon-Reasoning
Clef
Decision readingClef is tracked, but not publicly ranked yet. The profile exposes 6 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Released Oct 1, 2026 — see all recent releases
Clef will be repriced, updated or retired. Get each notice with its source and date. Follow model changes
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
Unranked
field median 52Not eligible for a public rank
Price
API rate not published
input median $0.95No comparable first-party hosted token rate
Speed
Not measured
field median 97 tok/sTime to first token not measured
Context
64Ktokens
field median 256,000Maximum output length is tracked separately
Strongest published evidence
Published rows are visible, but no category has enough eligible evidence for a comparative rank.
Validate before choosing
6 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.
Source-linked · 6 displayable benchmark rows
Follow model changesBenchmark ledger
External signals opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
External signals6 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Decision Index 0.3 Full ScoreDecision Index 0.3 | Score53.1 points | Versus best verified row Best verified: Perplexity Decider v1.1 (27B) · 62.8 points | Gap9.7 behind | WeightDisplay only | Benchmark exact |
| Decision Index 0.3 Knowledge | Score41.0 points | Versus best verified row Best verified: Quyet-1.0-Large · 47.8 points | Gap6.8 behind | WeightDisplay only | Benchmark exact |
| Decision Index 0.3 Language | Score51.6 points | Versus best verified row Best verified: Perplexity Decider v1.1 (27B) · 62.3 points | Gap10.7 behind | WeightDisplay only | Benchmark exact |
| Decision Index 0.3 Retrieval | Score60.7 points | Versus best verified row Best verified: Perplexity Decider v1.1 (27B) · 64.7 points | Gap4 behind | WeightDisplay only | Benchmark exact |
| Decision Index 0.3 Tools | Score77.0 points | Versus best verified row Best verified: Fastino GLiDE no-thinking (28B) · 82.7 points | Gap5.7 behind | WeightDisplay only | Benchmark exact |
| Decision Index 0.3 Arts | Score45.9 points | Versus best verified row Best verified: Torchcast Decision 27B · 52.8 points | Gap6.9 behind | WeightDisplay only | Benchmark exact |
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Base entry
Radar
Full release historyClef release history
Radar confirmed these at the source. Use Clef in your work? Explore Radar to follow supported changes and choose your alerts.
Radar
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- @cf/cloudflare/clefCloudflare Workers AI model documentation
- Context window
- 64KCloudflare Workers AI model documentation
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- text, image, videoCloudflare model card
- Output modalities
- structuredCloudflare model card
- Parameters
- Not sourced yet
- Availability
- Workers AI · Self-hosted Apache-2.0 weightsCloudflare Workers AI model documentation
- Cloud regions
- Not tracked yet
- Lifecycle
- activeCloudflare Workers AI model documentation
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordCloudflare Workers AI pricing
- Self-host
- Open weights available; hardware estimate not sourced
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Clef, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.
Clef is a open weight model with a 64K context window. No explicit reasoning mode is documented in this profile.
Released October 1, 2026 on Workers AI with Apache-2.0 weights. The hosted model has a 65,536-token window. The self-hosted example defaults to 16,384 input tokens; it is not the hosted limit.
Clef is an open-weight 27B decision model derived from Qwen/Qwen3.8-27B. It returns probabilities over typed schema choices rather than free-form text. Cloudflare comparison results remain display only and do not enter weighted rankings.
6 of 665 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Last updated October 8, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Published weights are available, but BenchLM does not yet have a sourced parameter and VRAM profile for this exact model. Hardware cost estimates stay unavailable until that sizing record is complete.
Estimate VRAM from known parametersQuestions
How does Clef perform overall in AI benchmarks?
Clef has 6 source-displayable benchmark rows, but it does not qualify for a public overall rank. The available rows remain visible by category without being converted into a site-wide score. Missing evidence stays blank instead of being estimated from an earlier model.
Is Clef open source?
Clef is an open-weight model from Cloudflare. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Does Clef have full benchmark coverage on BenchLM?
No. Clef currently has 6 source-displayable rows across 665 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Clef?
Clef has a documented context window of 64K. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.