Overview
Ling-3.1-flash is a language model from inclusionAI, the team behind Ant Group's artificial-general-intelligence programme. Ant Ling announced it on 30 September 2026 as a model of about 560 billion total parameters with about 25 billion activated per token and a context window of up to 1 million tokens, and said it plans to open-source the model soon. It is the successor in the Ling line to Ling-3.0-flash, a 124B model with 5.1B active parameters, so it is several times larger in both total and active parameters.
Unlike earlier Ling releases, Ling-3.1-flash did not ship with downloadable weights. It launched as a free hosted trial: OpenRouter lists it as inclusionai/ling-3.1-flash, a text-to-text hybrid reasoning model with reasoning on by default, served by Novita at a 262,144-token context, a 32,768-token output cap and a price of zero. TechNode reported that the free trial runs for two weeks at a 256,000-token context, and that inclusionAI plans to enable the larger window and release the model as open source after the trial.
Ant Ling positions the model across work, coding and healthcare. Its launch post headlines 1,673 Elo on GDPval-AA v2.1, 75.16 on FrontierSWE and 65.35 on HealthBench Professional, and its published chart sets Ling-3.1-flash against GPT-5.6 Sol, Claude Opus 5, Kimi K3, GLM 5.3, GLM 5.3 flash and DeepSeek-V4.1-Flash on twelve benchmarks spanning agentic work, terminal and software engineering, cybersecurity, finance, healthcare and multi-turn instruction following. Ant Ling notes that HealthBench Professional was evaluated in its AQ environment, and that Ling-3.1-flash's healthcare capabilities can only be experienced in AQ.
| Released | 2026-09-30 |
|---|---|
| License | Not yet published |
| Weights | API only |
| Parameters | ~560B total · ~25B activated per token (Mixture-of-Experts) |
| Context | Up to 1M tokens (designed); 262,144 tokens served during the trial |
| Max output | 32,768 tokens (OpenRouter trial endpoint) |
| Architecture | Hybrid reasoning Mixture-of-Experts |
| Modalities | Text |
| Status | Preview — free hosted trial; weights not yet published |
Benchmarks
Ling-3.1-flash against the models in Ant Ling's launch chart. A dash means the model was not shown for that benchmark. GDPval-AA is an Elo rating; all other rows are scores.
| Benchmark | Ling-3.1-flash | GPT-5.6 Sol | Claude Opus 5 | Kimi K3 | GLM 5.3 | GLM 5.3 flash | DeepSeek-V4.1-Flash |
|---|---|---|---|---|---|---|---|
| GDPval-AA v2.1 | 1673 Elo | 1588 Elo | 1708 Elo | 1524 Elo | 1644 Elo | 1641 Elo | 1600 Elo |
| τ³-Banking | 47.8 | 44.3 | 42.1 | 46 | 50.3 | 47.2 | 42.5 |
| SkillsBench | 68.7 | 73.5 | 63.7 | 63.6 | 59.4 | 61.3 | 71.3 |
| Automationbench (public) | 52.5 | 45.8 | 50.3 | 46.7 | 48.2 | 48.8 | 54.8 |
| Terminal-Bench 4.0 | 40.4 | 39.9 | 49 | 12.6 | 41.9 | 32.8 | 31.2 |
| CyberGym | 87.9 | 84.5 | — | 80 | 84.5 | — | 88.1 |
| FrontierSWE | 75.16 | — | — | 73.52 | 74.34 | 58.55 | — |
| SWE Atlas - Codebase QnA | 55.92 | 54 | 62 | 66 | 59 | 61.29 | 54.03 |
| Finance Agent v2 | 57.87 | 56.48 | 62.96 | 61.11 | 60.49 | 59.26 | 61.57 |
| HealthBench Professional | 65.35 | 60.76 | 59.8 | 49.56 | 49.56 | 49.07 | 50.37 |
| DRACO | 85.49 | 77.7 | 88.6 | 77.5 | 78.1 | 78.55 | 79.85 |
| MultiChallenge | 69.78 | 66.32 | 64.98 | 55.98 | 63.89 | 62.6 | 72.12 |
This model's scores
- FrontierSWE75.16%
- HealthBench Professional65.35%
- CyberGym87.9%
- DRACO85.49%
- Terminal-Bench 4.040.4%
Scores on a 0–100 scale (25-point gridlines); higher is better. Each benchmark links to its published source.
Strengths
- Roughly 560B total parameters with only about 25B active per token, according to Ant Ling
- Designed for up to a 1M-token context; the trial serves 262,144 tokens
- Led every model in Ant Ling's published chart on HealthBench Professional (65.35) and FrontierSWE (75.16)
- Free to try during the launch trial, including through OpenRouter
- Ant Ling says it plans to open-source the model
Best for
- Agentic office and knowledge work of the kind GDPval-AA measures
- Software-engineering agents working in terminals and real codebases
- Healthcare question answering, which Ant Ling says is available through its AQ environment
- Finance and banking agent workflows
How to access
| Provider | Model ID |
|---|---|
| OpenRouter ↗ | inclusionai/ling-3.1-flash |
Ling (open-weight) — every version
The full lineage of the Ling (open-weight) line, newest first. Every version has its own page — click any to compare specs, benchmarks and pricing.
| Version | Released | Context | License |
|---|---|---|---|
| Ling-3.1-flash | 2026-09-30 | 256K (trial) | Not yet published |
| Ling-3.0-tiny | 2026-08 | — | MIT |
| Ling-3.0-flashcurrent | 2026-08-02 | 256K | MIT |
FAQ
Is Ling-3.1-flash open source?
Not at launch. Ant Ling's 30 September 2026 announcement says it plans to open-source the model soon, but no weights or license had been published when it launched as a free hosted trial. Earlier Ling models such as Ling-3.0-flash were released under the MIT License.
How many parameters does Ling-3.1-flash have?
About 560 billion total parameters, with about 25 billion activated per token, according to Ant Ling. It is a Mixture-of-Experts model, so only a fraction of the weights run for each token.
How long a context does Ling-3.1-flash support?
Ant Ling says it supports up to a 1-million-token context. During the launch trial it is served at a shorter window: OpenRouter lists a 262,144-token context and a 32,768-token output cap.
How can I try Ling-3.1-flash?
At launch it was available free through a hosted trial, including on OpenRouter as inclusionai/ling-3.1-flash. TechNode reported that the free trial lasts two weeks.
How does Ling-3.1-flash compare with other models?
In Ant Ling's own launch chart it scored highest of the seven models shown on HealthBench Professional (65.35) and FrontierSWE (75.16), while Claude Opus 5 led on GDPval-AA v2.1, Terminal-Bench 4.0 and DRACO, and GPT-5.6 Sol led on SkillsBench. These are the maker's figures.