Skip to main content

Fastino LabsDecision modelActive

GLiDE

Popularityno data yet

n/ano search or usage data

Summary

GLiDE is Fastino’s API model for adaptive decisions. It starts with a quick assessment and spends extra reasoning when it is uncertain. A request describes a state and predefined actions. The response returns the selected action, confidence, and probabilities rather than a long answer.

Its API model ID is fastino/glide. Fastino publishes its own Decision Index results, but those values are not independently verified as a public benchmark.

GraduallyBench Decision

GLiDE

Partially tested
  • The test coverage is incomplete.
  • The functional test does not assess content quality.
  • Only text input was tested.
Show test details

Decisions

Local · German, English

Execution CPU. Precision BF16.

29 valid outputs from 32 attempted and 130 planned test slots.

No further scored metric is available for this test.

Response times are comparable only within the same environment and form no shared speed ranking. Where used, the test references were not independently reviewed by humans. Test coverage and methods differ by model. Each metric stands on its own; there is no combined overall score across tests. Data compiled on 11/10/2026. How we test · Download all Decision and Audio results as JSON

All benchmark results

Every published result with its source, test setup and comparison models.

Show all 20 published benchmark results

Page 1 of 2

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: CLadder accuracy (Show measurement, test conditions, and source)
Source value
88.7
Metric
CLadder accuracy
Unit
%
Benchmark version
0.2.1
Category
Decision Index 0.2.1
Direction
Higher is better
Source type
vendor-reported
Evaluator
Fastino Glide launch article
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Official scorer version=0.2.1; Run=Fastino full run; not yet in public leaderboard
Context
Provider full run with the official scorer; not an independent public leaderboard result.
Source Fastino Glide launch article
Decision Index 0.2.1: CRUXEval accuracy (Show measurement, test conditions, and source)
Source value
92.6
Metric
CRUXEval accuracy
Unit
%
Benchmark version
0.2.1
Category
Decision Index 0.2.1
Direction
Higher is better
Source type
vendor-reported
Evaluator
Fastino Glide launch article
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Official scorer version=0.2.1; Run=Fastino full run; not yet in public leaderboard
Context
Provider full run with the official scorer; not an independent public leaderboard result.
Source Fastino Glide launch article
ProofWriter 2026-10-02 open-world accuracy (Show measurement, test conditions, and source)
Source value
82.9
Metric
accuracy
Unit
%
Benchmark version
Fastino API alias glide, ProofWriter run 2026-10-02
Category
decision-model-benchmark
Direction
Higher is better
Sample
1800
Source type
vendor-reported
Evaluator
Ryan Porter, Anthus, Glide Decision Model evaluation
Status
active
Retrieved at
2026-10-17
Methodology
Vendor-reported result. ProofWriter open-world split, one answer per problem, Fastino API alias “glide”. First reported run on 2 October 2026. N=1800. Evaluator reports 1,800 open-world and 1,800 closed-world problems.
Context
Anthus reports a Jev-related evaluation and may have commercial or competitive interests, so this is conservatively classified vendor-reported. No model revision or full decoding configuration is pinned. The two runs are kept separate, not averaged; rerun AUROC values are not published.
Source Ryan Porter, Anthus, Glide Decision Model evaluation
ProofWriter 2026-10-02 closed-world accuracy (Show measurement, test conditions, and source)
Source value
71.8
Metric
accuracy
Unit
%
Benchmark version
Fastino API alias glide, ProofWriter run 2026-10-02
Category
decision-model-benchmark
Direction
Higher is better
Sample
1800
Source type
vendor-reported
Evaluator
Ryan Porter, Anthus, Glide Decision Model evaluation
Status
active
Retrieved at
2026-10-17
Methodology
Vendor-reported result. ProofWriter closed-world split, one answer per problem, Fastino API alias “glide”. First reported run on 2 October 2026. N=1800. Evaluator reports 1,800 open-world and 1,800 closed-world problems.
Context
Anthus reports a Jev-related evaluation and may have commercial or competitive interests, so this is conservatively classified vendor-reported. No model revision or full decoding configuration is pinned. The two runs are kept separate, not averaged; rerun AUROC values are not published.
Source Ryan Porter, Anthus, Glide Decision Model evaluation
ProofWriter 2026-10-03 requested rerun open-world accuracy (Show measurement, test conditions, and source)
Source value
76.4
Metric
accuracy
Unit
%
Benchmark version
Fastino API alias glide, ProofWriter rerun 2026-10-03
Category
decision-model-benchmark
Direction
Higher is better
Sample
1800
Source type
vendor-reported
Evaluator
Ryan Porter, Anthus, Glide Decision Model evaluation
Status
active
Retrieved at
2026-10-17
Methodology
Vendor-reported result. ProofWriter open-world split, one answer per problem, Fastino API alias “glide”. The 3 October rerun was requested by Fastino's CEO and used the same request as the earlier run. N=1800. Evaluator reports 1,800 open-world and 1,800 closed-world problems.
Context
Anthus reports a Jev-related evaluation and may have commercial or competitive interests, so this is conservatively classified vendor-reported. No model revision or full decoding configuration is pinned. The two runs are kept separate, not averaged; rerun AUROC values are not published.
Source Ryan Porter, Anthus, Glide Decision Model evaluation
ProofWriter 2026-10-03 requested rerun closed-world accuracy (Show measurement, test conditions, and source)
Source value
68.8
Metric
accuracy
Unit
%
Benchmark version
Fastino API alias glide, ProofWriter rerun 2026-10-03
Category
decision-model-benchmark
Direction
Higher is better
Sample
1800
Source type
vendor-reported
Evaluator
Ryan Porter, Anthus, Glide Decision Model evaluation
Status
active
Retrieved at
2026-10-17
Methodology
Vendor-reported result. ProofWriter closed-world split, one answer per problem, Fastino API alias “glide”. The 3 October rerun was requested by Fastino's CEO and used the same request as the earlier run. N=1800. Evaluator reports 1,800 open-world and 1,800 closed-world problems.
Context
Anthus reports a Jev-related evaluation and may have commercial or competitive interests, so this is conservatively classified vendor-reported. No model revision or full decoding configuration is pinned. The two runs are kept separate, not averaged; rerun AUROC values are not published.
Source Ryan Porter, Anthus, Glide Decision Model evaluation
StreamDecisionBench (Show measurement, test conditions, and source)
Source value
39.43
Metric
Mean log-AUC 0.5–8 s
Unit
%
Direction
No direction published
Sample
480
Source type
independent-evaluator
Evaluator
StreamDecisionBench GitHub README
Status
active
Retrieved at
2026-10-18
Methodology
Independent evaluation. Hosted API setting, exact source row “GLiDE (Fastino)”; provider Fastino, source command route `--provider fastino --model fastino/GLiDE`. Three passes over all 480 states per pass (8 scenarios in 4 families), sampled at a 2 s step; the source reports means. The README states hosted latency includes the remote service and internet round trip, and that other hosted providers use 32 workers. Exact provider/model release revision and additional request settings are not stated.
Source StreamDecisionBench GitHub README
StreamDecisionBench (Show measurement, test conditions, and source)
Source value
80.49
Metric
Mean untimed (%)
Unit
%
Direction
No direction published
Sample
480
Source type
independent-evaluator
Evaluator
StreamDecisionBench GitHub README
Status
active
Retrieved at
2026-10-18
Methodology
Independent evaluation. Hosted API setting, exact source row “GLiDE (Fastino)”; provider Fastino, source command route `--provider fastino --model fastino/GLiDE`. Three passes over all 480 states per pass (8 scenarios in 4 families), sampled at a 2 s step; the source reports means. The README states hosted latency includes the remote service and internet round trip, and that other hosted providers use 32 workers. Exact provider/model release revision and additional request settings are not stated.
Source StreamDecisionBench GitHub README
Decision Index 0.2.1: overall (chance-adjusted skill points) (Show measurement, test conditions, and source)
Source value
64.81
Metric
overall
Unit
points
Benchmark version
0.2.1
Category
Decision Index 0.2.1
Direction
Higher is better
Source type
vendor-reported
Evaluator
Fastino Glide launch article
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Official scorer version=0.2.1; Run=Fastino full run; not yet in public leaderboard
Context
Provider full run with the official scorer; not an independent public leaderboard result.
Source Fastino Glide launch article
Decision Index 0.2.1: Tools and Automation (chance-adjusted skill points) (Show measurement, test conditions, and source)
Source value
83.5
Metric
Tools and Automation
Unit
points
Benchmark version
0.2.1
Category
Decision Index 0.2.1
Direction
Higher is better
Source type
vendor-reported
Evaluator
Fastino Glide launch article
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Official scorer version=0.2.1; Run=Fastino full run; not yet in public leaderboard
Context
Provider full run with the official scorer; not an independent public leaderboard result.
Source Fastino Glide launch article
Decision Index 0.2.1: Knowledge and Reasoning (chance-adjusted skill points) (Show measurement, test conditions, and source)
Source value
62.9
Metric
Knowledge and Reasoning
Unit
points
Benchmark version
0.2.1
Category
Decision Index 0.2.1
Direction
Higher is better
Source type
vendor-reported
Evaluator
Fastino Glide launch article
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Official scorer version=0.2.1; Run=Fastino full run; not yet in public leaderboard
Context
Provider full run with the official scorer; not an independent public leaderboard result.
Source Fastino Glide launch article
Zero-shot IE spectrum: mixed-pool classification accuracy (Show measurement, test conditions, and source)
Source value
0.9792
Metric
classification accuracy (fraction correct)
Unit
ratio
Benchmark version
Zero-shot IE spectrum snapshot at repository commit c45a00c25d2731ac7047def97b91421aaff2f611
Category
typed-decision-classification
Direction
Higher is better
Sample
48
Source type
independent-evaluator
Evaluator
Zero-shot IE benchmark, pinned public result snapshot (c45a00c25d2731ac7047def97b91421aaff2f611)
Status
active
Retrieved at
2026-10-17
Methodology
Independent evaluation. Mixed-pool typed classification accuracy. Exact result key “GLiDE (Fastino)” in the evaluator's public spectrum JSON (SHA-256 d0e767ea3cd40088dc6492341f1c27a60d7c8d986d02eb2406cb1ee8a39df053); source commit c45a00c25d2731ac7047def97b91421aaff2f611. The evaluator defines one mixed pool of 48 classification questions and one recorded run per system. Recorded timestamp 2026-10-03 19:43 is published without a timezone. The source does not publish an immutable checkpoint/revision or complete decoding settings; no confidence interval is provided.
Context
This is a small custom evaluator-created test, not a standardized leaderboard. It is attached only to the exact public system label. The loaded weights or hosted serving revision are not pinned, so the result does not establish a current provider checkpoint score.
Source Zero-shot IE benchmark, pinned public result snapshot (c45a00c25d2731ac7047def97b91421aaff2f611)

Page 1 of 2

All specifications

Architecture

Model class
Adaptive reasoning decision model, not a chat model
Source: Model class

Input and output

Input
Application state and predefined actions as state
Source: Input
Reasoning
Starts with a fast assessment and allocates more reasoning when uncertain
Source: Reasoning

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking
Unknown
no source
Watermarking technique
Not known
no source

Licence and access

Access
Fastino API
Source: Access
Shutdown
None announced
no source

API

API model ID
fastino/glide
Source: API model ID

Further details

Output schema
Choice with a selected action, confidence, and probabilities
Source: Output schema
Evaluation
Fastino reports its own Decision Index results; the run is not verified as an independent public benchmark
Source: Evaluation

Sources and data date

Benchmark sources at a glance

Which independent evaluators tested this model. This is coverage, not a quality ranking.

No active result from the reviewed external evaluators can currently be attributed to this model. Other source evidence remains available below.

Without vendor claims and historical or disputed results; those stay labelled in the single values.

TypeEvidence and data date
Research statusResearch date October 4, 2026. 7 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not found in the inspected sources

independent-public-leaderboard

Note

The provider reports a full official-scorer run, but no independent public leaderboard result was found.

Not published

immutable-model-or-route-revision

Note

The zero-shot IE custom benchmark maps its exact public label to the profile task, but does not publish the loaded weight hash or immutable serving revision.

Not published

sampling-uncertainty

Note

The zero-shot IE small custom pools have no published confidence intervals. This gap is specific to those score cells.

Not found in the inspected sources

Exact model result in the public Decision Index 0.4.1 panel

Note

This index edition has no row that can be mapped to the profile repository/checkpoint exactly. This does not imply the model lacks results in other benchmarks.

Additional sourceFastino GLiDE announcement (retrieved October 3, 2026; October 4, 2026) · Fastino GLiDE announcement · Editorial description reviewed October 3, 2026
Additional sourceZero-shot IE benchmark, pinned public result snapshot (c45a00c25d2731ac7047def97b91421aaff2f611) (retrieved October 17, 2026)
Additional sourceRyan Porter, Anthus, Glide Decision Model evaluation (retrieved October 17, 2026)
Additional sourceStreamDecisionBench GitHub README (retrieved October 18, 2026)
Additional sourceBenchmark Heaven JevBench model page (retrieved October 20, 2026)
Additional sourceArtificial Analysis, Decision Index v1.0 launch article (retrieved October 21, 2026)