Jais 3 released
IFM · Model release
Source confirmed
Data as of October 15, 2026 · How the score is built
CurrentOpen WeightReasoning
Jais-3-32B
Decision readingJais-3-32B is tracked, but not publicly ranked yet. The profile exposes 2 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Released Oct 15, 2026 — see all recent releases
Jais-3-32B 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 49.8Not eligible for a public rank
Price
API rate not published
input median $0.75No comparable first-party hosted token rate
Speed
Not measured
field median 92 tok/sTime to first token not measured
Context
512Ktokens
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
2 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.
Source-linked · 2 displayable benchmark rows
Follow model changesCategory score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticWeight 22%1 benchmarkVerified | Score pending | 1 benchmark | Verified | |||
| CodingRank Not rankedWeight 20%1 benchmarkVerified | 59.0 | 1 benchmark | Verified | |||
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| KnowledgeWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MathWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured |
2 of 680 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic1/1 verified
- Coding1/1 verified
- ReasoningNot measured
- MultimodalNot measured
- KnowledgeNot measured
- MultilingualNot measured
- Inst. FollowingNot measured
- MathNot measured
Verified sourceProvisionalNot measured
Benchmark ledger
Coding 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.
Coding1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | Score72.4% | Versus best verified row Best verified: Claude Opus 5 · 96% | Gap23.6 behind | WeightDisplay only | Provider exact |
Agentic1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Terminal-Bench 2.1 | Score63.7% | Versus best verified row Best verified: SWE-2 · 92.8% | Gap29.1 behind | Weight8% ref. weight | Provider exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 2 rowsLineage
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
Jais-3-32B-UnoRadar
Full release historyJais-3-32B release history
Radar confirmed these at the source. Use Jais-3-32B 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.
- Weights model ID
- inception42/Jais-3-32BIFM model card
- Context window
- 512KIFM base model configuration
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- textIFM model card
- Output modalities
- textIFM model card
- Parameters
- Not sourced yet
- Availability
- Hugging Face · self-hosted inferenceIFM model card
- Cloud regions
- Not tracked yet
- Lifecycle
- activeIFM model card
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordIFM model card
- 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 Jais-3-32B, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.
Jais-3-32B is a open weight model with a 512K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Apache 2.0 weights for self-hosted Arabic and English text generation, with a 512K-token context window. IFM links vLLM and SGLang serving recipes; no exact first-party hosted token price is established.
IFM publishes Arabic and English reasoning weights under Apache 2.0. The model card uses High reasoning effort. Arabic results use provider-audited or translated tests and are not mapped to standard MMLU, GSM8K, IFEval, or long-context lanes. GDPval at a 75% threshold, text-only Apex-Agents subsets, WildClawBench, Arabic GAIA, and BrowseComp variants remain outside compatible score fields. The source-linked agentic rows are provider-reported. The card reports 88.6% on its cleaned Arabic MMLU set; this is not a standard MMLU score.
Jais-3-32B sits in the Jais-3-32B family with Jais-3-32B-Uno. 2 of 680 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Last updated October 15, 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 Jais-3-32B perform overall in AI benchmarks?
Jais-3-32B has 2 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 Jais-3-32B good for coding and programming?
Jais-3-32B has source-displayable benchmark coverage for coding and programming, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Jais-3-32B good for agentic tool use and computer tasks?
Jais-3-32B has source-displayable benchmark coverage for agentic tool use and computer tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Jais-3-32B open source?
Jais-3-32B is an open-weight model from IFM. 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.
Which sibling models are related to Jais-3-32B?
Jais-3-32B belongs to the Jais-3-32B family. Related tracked variants include Jais-3-32B-Uno. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does Jais-3-32B have full benchmark coverage on BenchLM?
No. Jais-3-32B currently has 2 source-displayable rows across 680 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 Jais-3-32B?
Jais-3-32B has a documented context window of 512K. 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.