Explore/benchmark/VisualAgentBench
V

THUDM/VisualAgentBenchAbandoned

Towards Large Multimodal Models as Visual Foundation Agents

benchmarkPythonApache-2.0
GitHubCompare
Refreshed 1h ago
OverviewActivity52wAlternativesDocs
Stars276
Forks14
HF Downloads30d
Last commit1y ago
Refreshed1h ago
Project healthAbandonedNo commits in 16 months.
Production readinessExperimentalGrowing but not yet battle-tested at scale.
Risk notesApache-2.0Verify license before production use.
AgentHub Score
55 / 100
Composite score from 6 signals. How we score →
Active project
55Score
Growth
84B+
Activity
30C
Documentation
50C
Maturity
68C+
Community
83B+
Production
58C
GitHub stars · 35 days observed276 +0.36% / 30d
snapshots
Repository activity · 35 days observedReal snapshots from pushed_at
inactivepushed
2026-07-262026-08-31
Practical assessment
Should you use it?

✓ Best for

  • Research and experimentation
  • Prototype development
  • Learning agentic patterns

◎ Strengths

  • Active community
  • Open source
  • Well-documented API

✕ Not ideal for

  • Untested at scale without validation
  • Teams without AI/ML expertise

⚠ Watch-outs

  • Review changelog before updating
  • Verify license for commercial use
Technical details
What's inside
LanguagePython
LicenseApache-2.0
Sourcegithub
Open source✗ No
Commercial use
Docs
Demo
Paper

AgentHub Score

55
Score 55/100
Below average

Alternatives

A
AgentBench
3.7k · benchmark
61
W
WebArena
1.6k · benchmark
61
A
ALFWorld
847 · benchmark
55
W
WebShop
588 · benchmark
55
Compare all →

Recent activity

Latest commit 1y ago1y ago
Indexed by AgentHub crawler1h ago
Monitor for new releasesongoing