New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
LLaDA2.2 Flash
About LLaDA2.2 Flash
LLaDA2.2 Flash is an AI model developed by Ant Group, in the language category, released in 2026, made available as an open-source model with 100B params. inclusionAI's LLaDA2.2-flash is an agent-oriented MoE diffusion language model with Levenshtein Editing. 100B total parameters (non-embedding) with 128K context. Introduces DELETE and INSERT control tokens for agentic editing. Scores 49.28 on SWE-bench Verified and 46.21 on MCP-Atlas.
On this page you'll find LLaDA2.2 Flash's full specifications, including a context window of 128K tokens, 4 benchmark results. Review provider pricing and benchmark scores below, or compare LLaDA2.2 Flash head-to-head with other language models.
Run LLaDA2.2 Flash locally — what to buy
Share this build ↗Sized to what LLaDA2.2 Flash actually needs (~128k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.
Software support
✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.
Community
No reports yet. Own this model on some hardware? Be the first to confirm it runs.
No comments yet. Start the discussion.
LLaDA2.2 Flash benchmark scores
Compare on the benchmark table →Scores on standardised evaluations. Higher is better, and the percentile shows where LLaDA2.2 Flash lands among every model we score on that benchmark.
Benchmarks only say so much. Have you run LLaDA2.2 Flash yourself? Tell everyone how it went — what it is good at, where it fell over, and on what hardware.
More models like LLaDA2.2 Flash
Frequently asked questions
What is LLaDA2.2 Flash? ▶
inclusionAI's LLaDA2.2-flash is an agent-oriented MoE diffusion language model with Levenshtein Editing. 100B total parameters (non-embedding) with 128K context. Introduces DELETE and INSERT control tokens for agentic editing. Scores 49.28 on SWE-bench Verified and 46.21 on MCP-Atlas. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.
Who created LLaDA2.2 Flash? ▶
LLaDA2.2 Flash was developed by Ant Group and released in 2026.
Is LLaDA2.2 Flash open source or proprietary? ▶
LLaDA2.2 Flash is released as open source — its weights are publicly available to download, run locally and fine-tune.
What is LLaDA2.2 Flash's context window? ▶
LLaDA2.2 Flash supports a context window of 128K tokens, and has 100B params.
How much does LLaDA2.2 Flash cost? ▶
Pricing for LLaDA2.2 Flash depends on the provider. See the providers table on this page for the latest API rates.
How does LLaDA2.2 Flash perform on benchmarks? ▶
LLaDA2.2 Flash is benchmarked across 4 evaluations on GenAIList, including SWE-bench Pro (30.1%). See the full benchmark table below and compare it with other models.
No videos yet. Know a good one? Add it below.
Know a great video about LLaDA2.2 Flash?
Add YouTube Video
Add Tweet/Discussion
Report an Issue
Help us maintain accurate information in our database.
Suggest an Edit
Tell us what needs to be changed or corrected for