Aug 5, 2026 · you are here
Hark HandoffNot publicly ranked · Price not listed
Model profile · Hark
Released Aug 5, 2026 — see all recent releases
Data as of August 5, 2026 · How the score is built
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
The sequence follows explicit supersedes links. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Aug 5, 2026 · you are here
Hark HandoffNot publicly ranked · Price not listed
research-preview · Research Preview
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Hark Handoff, but no weighted text-model benchmark result is published on the site yet. This page shows the metadata and separate protocol evidence we can verify now; a BenchLM score will appear only if compatible public evaluations land.
Hark Handoff is a proprietary model. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Hark introduced Handoff as a research preview on August 5, 2026. Access is currently application-based through Hark's beta sign-up; Hark says its broader platform will be available by the end of summer.
Official launch snapshot from Hark's August 5, 2026 Handoff announcement. Hark describes Handoff as a long-horizon computer-use agent that runs in a dedicated virtual computer with a browser, file system, and terminal. Its launch compares the system on Online-Mind2Web, WebTailBench, and internal browser-use evaluations, but the published Online-Mind2Web chart is not exposed as machine-readable values and the WebTailBench/internal results use Hark's own harness. BenchLM therefore records the release without copying non-reconciled values into comparable benchmark fields.
The profile has no source-displayable benchmark row yet.
Hark · Model release
Hark Handoff does not have any source-displayable benchmark rows yet, so this profile does not assign a public score or rank. Documented specifications remain visible, while score-led charts and claims stay unavailable until a published evaluation can be attached to the exact model.
No. Hark Handoff currently has 0 source-displayable rows across 381 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.
Hark Handoff's context window is not documented in a source tied to this exact model yet. The profile leaves the value unavailable instead of borrowing a limit from an earlier family member or an unverified route. Maximum output length remains a separate field.
Related resources
Last updated August 5, 2026. Runtime fields remain blank until a sourced snapshot exists.
Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.
Read a sample issueJoin 2,000+ readers.