MapikaDecision modelOpen source
Decider 2B
PopularityRank 92 of 876
52out of 100-9 vs. last month
Summary
Decider 2B occupies the compact middle of the text-based Decider family. The 1.9-billion-parameter checkpoint processes typed questions over a state and distributes probability across 2 to 255 options. Its context window covers 32,000 tokens. The readout happens in one pass, with the answer schema defined before the call.
In the text-based line, Decider 2B sits between Decider 0.8B and Decider 4B.
All benchmark results
Every published result with its source, test setup and comparison models.
Show all 89 published benchmark results
Page 1 of 8
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.
DecideBench overall accuracy (Show measurement, test conditions, and source)
- Source value
- 63.2
- Score
- 63.2
- Metric
- accuracy
- Unit
- %
- Category
- decision
- Direction
- Higher is better
- Sample
- 400
- Source type
- independent-evaluator
- Evaluator
- DecideBench
- Status
- active
- Retrieved at
- 2026-10-18
- Methodology
- Independent evaluation. DecideBench results read from the repository main README (not pinned to a commit); 400 multiple-choice decisions in 200 contrastive pairs, measured 2026-09-28 through 2026-10-09. Exact per-model checkpoint revision and request sampling settings are not reported. Exact row is Decider-2B (self-hosted) on an NVIDIA L4 at four requests in flight. The README describes solved per-option examples and appended examples for other open reproductions, but does not give a per-entry request template or exact checkpoint revision.
DecideBench pair accuracy (Show measurement, test conditions, and source)
- Source value
- 41
- Score
- 41
- Metric
- pair accuracy
- Unit
- %
- Category
- decision
- Direction
- Higher is better
- Sample
- 200
- Source type
- independent-evaluator
- Evaluator
- DecideBench
- Status
- active
- Retrieved at
- 2026-10-18
- Methodology
- Independent evaluation. DecideBench results read from the repository main README (not pinned to a commit); 400 multiple-choice decisions in 200 contrastive pairs, measured 2026-09-28 through 2026-10-09. Exact per-model checkpoint revision and request sampling settings are not reported. Exact row is Decider-2B (self-hosted) on an NVIDIA L4 at four requests in flight. The README describes solved per-option examples and appended examples for other open reproductions, but does not give a per-entry request template or exact checkpoint revision.
DecideBench action_review accuracy (Show measurement, test conditions, and source)
- Source value
- 56
- Score
- 56
- Metric
- accuracy on task family action_review
- Unit
- %
- Category
- decision
- Direction
- Higher is better
- Sample
- 50
- Source type
- independent-evaluator
- Evaluator
- DecideBench
- Status
- active
- Retrieved at
- 2026-10-18
- Methodology
- Independent evaluation. DecideBench results read from the repository main README (not pinned to a commit); 400 multiple-choice decisions in 200 contrastive pairs, measured 2026-09-28 through 2026-10-09. Exact per-model checkpoint revision and request sampling settings are not reported. Exact row is Decider-2B (self-hosted) on an NVIDIA L4 at four requests in flight. The README describes solved per-option examples and appended examples for other open reproductions, but does not give a per-entry request template or exact checkpoint revision.
DecideBench agent_routing accuracy (Show measurement, test conditions, and source)
- Source value
- 66
- Score
- 66
- Metric
- accuracy on task family agent_routing
- Unit
- %
- Category
- decision
- Direction
- Higher is better
- Sample
- 50
- Source type
- independent-evaluator
- Evaluator
- DecideBench
- Status
- active
- Retrieved at
- 2026-10-18
- Methodology
- Independent evaluation. DecideBench results read from the repository main README (not pinned to a commit); 400 multiple-choice decisions in 200 contrastive pairs, measured 2026-09-28 through 2026-10-09. Exact per-model checkpoint revision and request sampling settings are not reported. Exact row is Decider-2B (self-hosted) on an NVIDIA L4 at four requests in flight. The README describes solved per-option examples and appended examples for other open reproductions, but does not give a per-entry request template or exact checkpoint revision.
DecideBench claim_support accuracy (Show measurement, test conditions, and source)
- Source value
- 42
- Score
- 42
- Metric
- accuracy on task family claim_support
- Unit
- %
- Category
- decision
- Direction
- Higher is better
- Sample
- 50
- Source type
- independent-evaluator
- Evaluator
- DecideBench
- Status
- active
- Retrieved at
- 2026-10-18
- Methodology
- Independent evaluation. DecideBench results read from the repository main README (not pinned to a commit); 400 multiple-choice decisions in 200 contrastive pairs, measured 2026-09-28 through 2026-10-09. Exact per-model checkpoint revision and request sampling settings are not reported. Exact row is Decider-2B (self-hosted) on an NVIDIA L4 at four requests in flight. The README describes solved per-option examples and appended examples for other open reproductions, but does not give a per-entry request template or exact checkpoint revision.
DecideBench content_moderation accuracy (Show measurement, test conditions, and source)
- Source value
- 66
- Score
- 66
- Metric
- accuracy on task family content_moderation
- Unit
- %
- Category
- decision
- Direction
- Higher is better
- Sample
- 50
- Source type
- independent-evaluator
- Evaluator
- DecideBench
- Status
- active
- Retrieved at
- 2026-10-18
- Methodology
- Independent evaluation. DecideBench results read from the repository main README (not pinned to a commit); 400 multiple-choice decisions in 200 contrastive pairs, measured 2026-09-28 through 2026-10-09. Exact per-model checkpoint revision and request sampling settings are not reported. Exact row is Decider-2B (self-hosted) on an NVIDIA L4 at four requests in flight. The README describes solved per-option examples and appended examples for other open reproductions, but does not give a per-entry request template or exact checkpoint revision.
DecideBench returns_policy accuracy (Show measurement, test conditions, and source)
- Source value
- 46
- Score
- 46
- Metric
- accuracy on task family returns_policy
- Unit
- %
- Category
- decision
- Direction
- Higher is better
- Sample
- 50
- Source type
- independent-evaluator
- Evaluator
- DecideBench
- Status
- active
- Retrieved at
- 2026-10-18
- Methodology
- Independent evaluation. DecideBench results read from the repository main README (not pinned to a commit); 400 multiple-choice decisions in 200 contrastive pairs, measured 2026-09-28 through 2026-10-09. Exact per-model checkpoint revision and request sampling settings are not reported. Exact row is Decider-2B (self-hosted) on an NVIDIA L4 at four requests in flight. The README describes solved per-option examples and appended examples for other open reproductions, but does not give a per-entry request template or exact checkpoint revision.
DecideBench review_sentiment accuracy (Show measurement, test conditions, and source)
- Source value
- 70
- Score
- 70
- Metric
- accuracy on task family review_sentiment
- Unit
- %
- Category
- decision
- Direction
- Higher is better
- Sample
- 50
- Source type
- independent-evaluator
- Evaluator
- DecideBench
- Status
- active
- Retrieved at
- 2026-10-18
- Methodology
- Independent evaluation. DecideBench results read from the repository main README (not pinned to a commit); 400 multiple-choice decisions in 200 contrastive pairs, measured 2026-09-28 through 2026-10-09. Exact per-model checkpoint revision and request sampling settings are not reported. Exact row is Decider-2B (self-hosted) on an NVIDIA L4 at four requests in flight. The README describes solved per-option examples and appended examples for other open reproductions, but does not give a per-entry request template or exact checkpoint revision.
DecideBench support_intent accuracy (Show measurement, test conditions, and source)
- Source value
- 96
- Score
- 96
- Metric
- accuracy on task family support_intent
- Unit
- %
- Category
- decision
- Direction
- Higher is better
- Sample
- 50
- Source type
- independent-evaluator
- Evaluator
- DecideBench
- Status
- active
- Retrieved at
- 2026-10-18
- Methodology
- Independent evaluation. DecideBench results read from the repository main README (not pinned to a commit); 400 multiple-choice decisions in 200 contrastive pairs, measured 2026-09-28 through 2026-10-09. Exact per-model checkpoint revision and request sampling settings are not reported. Exact row is Decider-2B (self-hosted) on an NVIDIA L4 at four requests in flight. The README describes solved per-option examples and appended examples for other open reproductions, but does not give a per-entry request template or exact checkpoint revision.
DecideBench ticket_triage accuracy (Show measurement, test conditions, and source)
- Source value
- 64
- Score
- 64
- Metric
- accuracy on task family ticket_triage
- Unit
- %
- Category
- decision
- Direction
- Higher is better
- Sample
- 50
- Source type
- independent-evaluator
- Evaluator
- DecideBench
- Status
- active
- Retrieved at
- 2026-10-18
- Methodology
- Independent evaluation. DecideBench results read from the repository main README (not pinned to a commit); 400 multiple-choice decisions in 200 contrastive pairs, measured 2026-09-28 through 2026-10-09. Exact per-model checkpoint revision and request sampling settings are not reported. Exact row is Decider-2B (self-hosted) on an NVIDIA L4 at four requests in flight. The README describes solved per-option examples and appended examples for other open reproductions, but does not give a per-entry request template or exact checkpoint revision.
local-jev-bench transfer-v4 accuracy (Show measurement, test conditions, and source)
- Source value
- 73
- Score
- 73
- Metric
- accuracy on transfer-v4
- Unit
- %
- Direction
- Higher is better
- Source type
- community-reported
- Evaluator
- local-jev-bench
- Status
- active
- Retrieved at
- 2026-10-22
- Methodology
- Community-reported result. Decider-2B was evaluated with Ollaya on the local transfer-v4 set. The report gives accuracy as a percentage; both Decider sizes ran in Ollaya on CPU (F32). Study/result reference: local-jev-bench; all engines remeasured 2026-10-14 to 2026-10-16; the three backfilled tasks were added 2026-10-12
- Context
- The report names model size and the Ollaya runner but gives no immutable checkpoint revision. Cell-specific sample counts and confidence intervals are not provided.
local-jev-bench BANKING77-20 accuracy (Show measurement, test conditions, and source)
- Source value
- 91
- Score
- 91
- Metric
- accuracy on BANKING77-20
- Unit
- %
- Direction
- Higher is better
- Source type
- community-reported
- Evaluator
- local-jev-bench
- Status
- active
- Retrieved at
- 2026-10-22
- Methodology
- Community-reported result. Decider-2B was evaluated with Ollaya on the local BANKING77-20 set. The report gives accuracy as a percentage; both Decider sizes ran in Ollaya on CPU (F32). Study/result reference: local-jev-bench; all engines remeasured 2026-10-14 to 2026-10-16; the three backfilled tasks were added 2026-10-12
- Context
- The report names model size and the Ollaya runner but gives no immutable checkpoint revision. Cell-specific sample counts and confidence intervals are not provided.
Page 1 of 8
Popularity compared
How often the model is searched for, used and mentioned, compared with every model of its category.
Popularity index
0 to 100, higher is more popular
20 of 37 models
As of November 2026 · Source: gradually.ai popularity index
Over time
Weekly values from October 18, 2026 to November 6, 2026
Decider 2BGLiNER2.5-Decide 56Clef 52Clef-Flash 51Laya Multilingual 46
Method changes in the timeline, a jump at these points is no market event:
- 1November 1, 2026: Value only with search or usage data, 30-day attention
What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.
Decider 2B compared
- 1Decider 2B vs. GLiNER2.5-Decide37 shared tests
- 2Decider 2B vs. Clef-Flash37 shared tests
- 3Decider 2B vs. Kev 0.8B37 shared tests
- 4Decider 2B vs. Decider 4B47 shared tests
- 5Decider 2B vs. Jev10 shared tests
- 6Decider 2B vs. Intern-Decision-4B37 shared tests
- 7Decider 2B vs. Kev 9B37 shared tests
- 8Decider 2B vs. Julia 147 shared tests
- 9Decider 2B vs. Intern-Decision-0.8B37 shared tests
Similar models
More models of the same kind as Decider 2B, chosen by model line, developer, size, price and release date.
- Decider 2B VisionMapika · same developer
- Decider 4BMapika · same developer
- Decider 0.8BMapika · same developer
- Decider 35B A3BMapika · same developer
- Decider 35B A3B NVFP4Mapika · same developer
- Intern-Decision-2BInternLM · similar size
- d1-2BLiquid AI · similar size
- Strands Decider 2BAWS Strands · similar size
All specifications
Architecture
Input and output
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
API
Further details
Sources and data date
Show all 18 sources
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.