LBS-27B Benchmarks, Specifications & Availability

LBS-27B

Explore LBS-27B from InclusionAI: published specifications, source-linked vendor benchmarks, independent evaluator coverage and recorded pricing when available.

Published specifications

Provider: InclusionAI
Access: Open weights
License: Apache 2.0
Context window: 262144
Total parameters: Not published
Active parameters: Not published
Released: 2026-10-26
Modalities: text, image
Family: LBS

Model card & announcement · Website

Model notes

Open BF16 weights verified from InclusionAI. Visual observation and GUI grounding based on Qwen3.8-27B; crop_image actions require an external crop executor, and GUI operation requires a separate executor. Publisher model name indicates 27B but Hugging Face metadata reports conflicting tensor and total parameter counts, so exact parameters remain unfilled. The official text configuration specifies 262,144 max positions. No exact OpenRouter route was found. Vendor benchmark results use agentic zoom with up to three crop calls; its PerceptionBench judge differs from peer references.

Compare LBS-27B with other models →Compare subscription plans Explore data coverage

Pricing · OpenRouter

No OpenRouter pricing is recorded for this model. Missing rates are not free.

Official / vendor benchmarks

Default headline records. Own-vendor, peer-vendor and third-party provenance remain visible in evidence; configurations may differ.

Official / vendor headline scores; expand evidence for every record
Benchmark / evaluator	Headline score	Evidence
ScreenSpot-Pro	81.2%unknown effort	All 1 recorded result & sources 81.2% · raw 81.15 % Headline · unknown effort · Own vendor Source/record date: 2026-10-27 Harness: InclusionAI agentic zoom, up to three crop calls. Official checkpoint results. PerceptionBench uses self-hosted Deepseekv4-flash-0731 judge; reference chart peers use GPT-oss-120B. Execution date and exact effort unpublished. https://huggingface.co/inclusionAI/LBS-27B/blob/e6ab883fa2b1d2579bf2616d38b6989b4af0333d/README.md
OS-World-G Refine (InclusionAI agentic zoom)	84.6%unknown effort	All 1 recorded result & sources 84.6% · raw 84.57 % Headline · unknown effort · Own vendor Source/record date: 2026-10-27 Harness: InclusionAI agentic zoom, up to three crop calls. Official checkpoint results. PerceptionBench uses self-hosted Deepseekv4-flash-0731 judge; reference chart peers use GPT-oss-120B. Execution date and exact effort unpublished. https://huggingface.co/inclusionAI/LBS-27B/blob/e6ab883fa2b1d2579bf2616d38b6989b4af0333d/README.md
PerceptionBench (InclusionAI agentic zoom)	59.7%unknown effort	All 1 recorded result & sources 59.7% · raw 59.67 % Headline · unknown effort · Own vendor Source/record date: 2026-10-27 Harness: InclusionAI agentic zoom, up to three crop calls. Official checkpoint results. PerceptionBench uses self-hosted Deepseekv4-flash-0731 judge; reference chart peers use GPT-oss-120B. Execution date and exact effort unpublished. https://huggingface.co/inclusionAI/LBS-27B/blob/e6ab883fa2b1d2579bf2616d38b6989b4af0333d/README.md
HR-Bench 4K (InclusionAI agentic zoom)	89.1%unknown effort	All 1 recorded result & sources 89.1% · raw 89.13 % Headline · unknown effort · Own vendor Source/record date: 2026-10-27 Harness: InclusionAI agentic zoom, up to three crop calls. Official checkpoint results. PerceptionBench uses self-hosted Deepseekv4-flash-0731 judge; reference chart peers use GPT-oss-120B. Execution date and exact effort unpublished. https://huggingface.co/inclusionAI/LBS-27B/blob/e6ab883fa2b1d2579bf2616d38b6989b4af0333d/README.md
HR-Bench 8K (InclusionAI agentic zoom)	87.8%unknown effort	All 1 recorded result & sources 87.8% · raw 87.75 % Headline · unknown effort · Own vendor Source/record date: 2026-10-27 Harness: InclusionAI agentic zoom, up to three crop calls. Official checkpoint results. PerceptionBench uses self-hosted Deepseekv4-flash-0731 judge; reference chart peers use GPT-oss-120B. Execution date and exact effort unpublished. https://huggingface.co/inclusionAI/LBS-27B/blob/e6ab883fa2b1d2579bf2616d38b6989b4af0333d/README.md

Independent evaluators

Evaluator harnesses are distinct from vendor measurements. Missing coverage is not a failed test.

No independent evaluator results are recorded for this model.

Read how we select and source scores or the comparison guide.