Holo1-7B
Holo1-7B is available now for agents, long context, and vision with open-source and 128K context; evaluate it while provider pricing coverage matures.
- Family
- Holo
- Released
- 2025-06-03
- Context
- 128K
- Parameters
- 7
- Specialization
- computer-use
- Openness
- Open source
- License
- Apache 2.0OSI-approvedPermitted
- Weights
- Available
- Code
- Unknown
- Training
- Supervised Fine-tuning
No tracked provider 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.
Overview
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.
Providers
No active provider routes are tracked for this model yet.
Capabilities
Benchmark peer barsfor Agents
No task-mapped benchmark peers are available for this model yet.
Benchmark scores(2)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| 76.2 | UI Localization Benchmarks (average) - avg across Screenspot, Screenspot-V2, Screenspot-Pro, GroundUI-Web, WebClickObserved 2025-06-03 | — | ||
| 92.2 | WebVoyager - with Surfer-H agentObserved 2025-06-03 | — |
Migration checks
No linked migration route is available for this model yet.
No tracked provider pricing is available yet.