LLM Reference

Holo1-7B

Released
2025-06-03
Last refreshed
2026-06-07
Status
Researched 44d ago
Open sourceCommercial use: permittedMultimodalAgentsLong contextVisionAgentsVision

Holo1-7B is available now for agents, long context, and vision with open-source and 128k context; evaluate it while provider pricing coverage matures.

Use it for

  • Teams evaluating agents, long context, and vision
  • Workloads that can use a 128k context window

Do not use it for

  • Cost-sensitive launches that need sourced token pricing
  • Strict JSON or tool-calling flows
  • Teams that need a tracked hosted API route today
Specifications
Family
Holo
Released
2025-06-03
Context
128k
Parameters
7
Specialization
computer-use
Openness
Open source
License
Apache 2.0OSI-approvedCommercial use: permitted
Weights
Available
Code
Unknown
Training
Supervised Fine-tuning
Created by

Agentic AI for Action

Paris, France
Founded 2023
Website
Pricing

No tracked provider token pricing is available yet.

About

Holo1-7B is H Company's 7B-parameter open-weights Vision-Language Model, the flagship of the Holo1 family. Fine-tuned from Qwen2.5-VL-7B-Instruct for GUI localization and web automation. Achieves 76.2% average accuracy on UI localization benchmarks and 92.2% success rate on WebVoyager when paired with Surfer-H at $0.13 per task.

Holo1-7B is H Company's 7B-parameter open-weights Vision-Language Model, the flagship of the Holo1 family. Fine-tuned from Qwen2.5-VL-7B-Instruct for GUI localization and web automation. Achieves 76.2% average accuracy on UI localization benchmarks and 92.2% success rate on WebVoyager when paired with Surfer-H at $0.13 per task.

Holo1-7B has a 128k-token context window.

Top use-case fit: coding, agents, and build tasks

Agents

Included by capability and metadata signals in the decision map.

Long context

Included by capability and metadata signals in the decision map.

Vision

Included by capability and metadata signals in the decision map.

Provider price ladder

No tracked provider token pricing is available for this model yet.

Capabilities

VisionMultimodal

Benchmark peer barsfor Agents

No task-mapped benchmark peers are available for this model yet.

Benchmark scores(2)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
UI Localization Average76.2UI Localization Benchmarks (average) - avg across Screenspot, Screenspot-V2, Screenspot-Pro, GroundUI-Web, WebClickObserved 2025-06-03Source
WebVoyager92.2WebVoyager - with Surfer-H agentObserved 2025-06-03Source

Migration checks

No linked migration route is available for this model yet.

Frequently asked questions

What is the context window of Holo1-7B?

Holo1-7B has a context window of 128k tokens.

When was Holo1-7B released?

Holo1-7B was released on 2025-06-03.

What benchmarks has Holo1-7B been tested on?

Holo1-7B has been evaluated on 2 benchmarks, including UI Localization Average, WebVoyager.