Ling 3.1 Flash released
InclusionAI · Model release
Source confirmed
Data as of September 30, 2026 · How the score is built
CurrentProprietaryReasoning
Released Sep 29, 2026262K contextVercel AI Gateway Ling 3.1 Flash listing
Ling 3.1 Flash
Decision readingLing 3.1 Flash 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 29, 2026 — see all recent releases
Ling 3.1 Flash 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 50.6Not eligible for a public rank
Price
API rate not published
input median $1No comparable first-party hosted token rate
Speed
Not measured
field median 92 tok/sTime to first token not measured
Context
262Ktokens
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. No comparable first-party API token rate is published.
Source-linked · 8 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 |
|---|---|---|---|---|---|---|
| AgenticRank Not rankedWeight 22%5 benchmarksVerified | 81.0 | 5 benchmarks | Verified | |||
| CodingWeight 20%2 benchmarksVerified | Score pending | 2 benchmarks | 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%1 benchmarkVerified | Score pending | 1 benchmark | Verified | |||
| 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 |
8 of 491 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.
- Agentic5/5 verified
- Coding2/2 verified
- ReasoningNot measured
- MultimodalNot measured
- Knowledge1/1 verified
- 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.
Coding2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| terminalBench4 | Score40.4% | Versus best verified row Best verified: Ling 3.1 Flash · 40.4% | GapBest verified | WeightDisplay only | |
| SWE-Atlas Codebase QnA | Score55.9% | Versus best verified row Best verified: Muse Spark 1.3 · 59.4% | Gap3.5 behind | WeightDisplay only |
Agentic5 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| AutomationBench | Score52.5% | Versus best verified row Best verified: DeepSeek V4.1 Flash · 54.8% | Gap2.3 behind | Weight5% ref. weight | |
| skillsBench | Score68.7% | Versus best verified row Best verified: Qwen3.8 Max · 70.2% | Gap1.5 behind | WeightDisplay only | |
| CyberGym | Score87.9% | Versus best verified row Best verified: MiMo-V2.6-Flash · 95.1% | Gap7.2 behind | WeightDisplay only | |
| Finance Agent v2 | Score57.9% | Versus best verified row Best verified: Gemini 4 Argon · 65.4% | Gap7.5 behind | WeightDisplay only | |
| DRACOData Research and Analysis with Complex Operations | Score85.5% | Versus best verified row Best verified: Claude Opus 5 · 88.6% | Gap3.1 behind | WeightDisplay only |
Knowledge1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| HealthBench Professional | Score65.3% | Versus best verified row Best verified: Claude Sonnet 5.5 · 69.2% | Gap3.9 behind | WeightDisplay only |
Bars run 0–100; the dark tick marks the best source-verified value
All 8 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.
Flash
Radar
Full release historyLing 3.1 Flash release history
Radar confirmed these at the source. Use Ling 3.1 Flash 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
- inclusionai/ling-3.1-flashVercel AI Gateway availability
- Context window
- 262KVercel AI Gateway availability
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not disclosed by the provider
- Availability
- Ling 3.1 Flash is available through Vercel AI Gateway via Novita with a 262,144-token context and up to 32,768 output tokens. Vercel lists free promotional access through October 13, 2026. InclusionAI says weights will be released soon; a public checkpoint and license are not yet confirmed.
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordVercel AI Gateway availability
- 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 Ling 3.1 Flash, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.
Ling 3.1 Flash is a proprietary model with a 262K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Ling 3.1 Flash is available through Vercel AI Gateway via Novita with a 262,144-token context and up to 32,768 output tokens. Vercel lists free promotional access through October 13, 2026. InclusionAI says weights will be released soon; a public checkpoint and license are not yet confirmed.
InclusionAI reports approximately 560B total parameters and 25B active parameters per token. The launch announcement claims up to 1M context, while the current Vercel route serves 262,144 tokens. Eight named benchmark values come from the supplied Ant Ling launch screenshots captured September 30, 2026; harnesses and grading settings are not documented there. HealthBench Professional was evaluated in the AQ environment, and the announced healthcare capabilities are currently available only in AQ. These are provider-reported results, not independent measurements or clinical certification. Version-ambiguous results and custom coding experiments remain outside benchmark fields.
Its explicit predecessor is Ling 3.0 Flash. 8 of 491 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Last updated September 30, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does Ling 3.1 Flash perform overall in AI benchmarks?
Ling 3.1 Flash 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.
Is Ling 3.1 Flash good for knowledge and understanding?
Ling 3.1 Flash has source-displayable benchmark coverage for knowledge and understanding, 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 Ling 3.1 Flash good for coding and programming?
Ling 3.1 Flash 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 Ling 3.1 Flash good for agentic tool use and computer tasks?
Ling 3.1 Flash 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.
Does Ling 3.1 Flash have full benchmark coverage on BenchLM?
No. Ling 3.1 Flash currently has 8 source-displayable rows across 491 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 Ling 3.1 Flash?
Ling 3.1 Flash has a documented context window of 262K. 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.