# LLaDA2.2-flash Benchmark Scores & Performance

> LLaDA2.2-flash by InclusionAI has 8 source-displayable benchmark rows but no public overall score. It remains unranked.

Canonical page: https://benchlm.ai/models/llada2-2-flash

Last updated: September 10, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | InclusionAI |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 128K |
| Official model card | [InclusionAI LLaDA2.2-flash model card](https://huggingface.co/inclusionAI/LLaDA2.2-flash) |
| Overall Score | Coming soon |
| Overall Rank | Unranked |

## Family & Coverage

- Family: LLaDA2.2
- Variant: flash
- Benchmarks covered: 8 of 434
- Sibling models: [LLaDA2.2-mini](/models/llada2-2-mini)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score |
|-----------|-------|
| [τ²-bench results](/benchmarks/tau2-bench) | 80.3% |
| [Claw-Eval](/benchmarks/claw-eval) | 64.2% |
| [PinchBench](/benchmarks/pinchbench) | 81.7% |
| [MCP Atlas](/benchmarks/mcpatlas) | 46.2% |
| [BFCL v4](/benchmarks/bfcl-v4) | 60.8% |

## Coding Benchmarks

| Benchmark | Score |
|-----------|-------|
| [SWE-bench Verified](/benchmarks/swe-bench-verified) | 49.3% |
| [SWE-bench Pro](/benchmarks/swe-bench-pro) | 30.1% |
| [SWE Multilingual](/benchmarks/swe-bench-multilingual) | 25% |

## Other InclusionAI Models

- [Ling 3.0 Flash](/models/ling-3-0-flash) - Score: 47.51
- [Ling 2.6 Flash](/models/ling-2-6-flash) - Score: 40.3
- [Ling 3.0 Flash VL](/models/ling-3-0-flash-vl) - Score: not computed
- [Ling 3.0 Flash FP8](/models/ling-3-0-flash-fp8) - Score: not computed
- [Ling 3.0 Tiny](/models/ling-3-0-tiny) - Score: not computed
- [LLaDA2.2-mini](/models/llada2-2-mini) - Score: not computed
- [Ling 3.0 Flash Fin](/models/ling-3-0-flash-fin) - Score: not computed