GLiDE released
Fastino · Model release
Source confirmed
Data as of October 1, 2026 · How the score is built
CurrentProprietaryReasoning
GLiDE
Decision readingGLiDE is tracked, but not publicly ranked yet. The profile exposes 8 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Released Sep 30, 2026 — see all recent releases
GLiDE will be repriced, updated or retired. Get each notice with its source and date. Follow model changes
Share or export
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 52.4Not eligible for a public rank
Price
$0.30input / $0 output
input median $0.95blended $0.15
Speed
Not measured
field median 89 tok/sTime to first token not measured
Context
40Ktokens
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
8 published rows leave some tracked benchmark slots empty. Independent runtime speed has not been measured.
Source-linked · 8 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 signals8 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Decision Index 0.2.1 (Fastino report) | Score64.81 skill points | Versus best verified row Best verified: GLiDE · 64.81 skill points | GapBest verified | WeightDisplay only | Provider exact |
| Knowledge and Reasoning (Fastino report) | Score62.9 skill points | Versus best verified row Best verified: GLiDE · 62.9 skill points | GapBest verified | WeightDisplay only | Provider exact |
| Language Understanding (Fastino report) | Score63.8 skill points | Versus best verified row Best verified: GLiDE · 63.8 skill points | GapBest verified | WeightDisplay only | Provider exact |
| Retrieval and Classification (Fastino report) | Score60.9 skill points | Versus best verified row Best verified: GLiDE · 60.9 skill points | GapBest verified | WeightDisplay only | Provider exact |
| Tools and Automation (Fastino report) | Score83.5 skill points | Versus best verified row Best verified: GLiDE · 83.5 skill points | GapBest verified | WeightDisplay only | Provider exact |
| Arts and Human Taste (Fastino report) | Score46.0 skill points | Versus best verified row Best verified: GLiDE · 46.0 skill points | GapBest verified | WeightDisplay only | Provider exact |
| CLadder (Fastino report) | Score88.7% | Versus best verified row Best verified: GLiDE · 88.7% | GapBest verified | WeightDisplay only | Provider exact |
| CRUXEval (Fastino report) | Score92.6% | Versus best verified row Best verified: GLiDE · 92.6% | GapBest verified | WeightDisplay only | Provider 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.
Decision-system
Radar
Full release historyGLiDE release history
Radar confirmed these at the source. Use GLiDE 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
- fastino/GLiDEFastino GLiDE API reference
- Context window
- 40KFastino model catalog
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- textFastino GLiDE API reference
- Output modalities
- typed JSONFastino GLiDE API reference
- Parameters
- Not disclosed by the provider
- Availability
- Fastino APIFastino model catalog
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Noul, Choice, and Score answers with probabilities and confidence. Each rendered question fits 40,000 tokens; Choice and Score accept up to 255 options or levels. Input usage sums internal passes across questions.Fastino GLiDE API reference
- Prompt caching
- Not documented in the pricing recordFastino GLiDE pricing
- Self-host
- Weights are not published
- 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 GLiDE, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.
GLiDE is a proprietary model with a 40K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Fastino released GLiDE on September 30, 2026, for typed decisions with adaptive reasoning. Fastino reports 64.81 chance-adjusted skill points on Decision Index 0.2.1; the model is not listed on the public leaderboard. Eight exact published metrics are stored separately from other harnesses and general rankings. The API returns Noul, Choice, or Score answers with probabilities and confidence. Each rendered question prompt must fit 40,000 tokens; input usage sums internal passes across questions. Parameter count and downloadable GLiDE weights are not published in the reviewed sources.
8 of 645 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Last updated October 1, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does GLiDE perform overall in AI benchmarks?
GLiDE has 8 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.
Does GLiDE have full benchmark coverage on BenchLM?
No. GLiDE currently has 8 source-displayable rows across 645 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 GLiDE?
GLiDE has a documented context window of 40K. 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.