Benchmark profile
ZeroBench
A multi-step visual reasoning benchmark with pass@5 reporting and optional tool use.
Data verifiedBenchmark score on ZeroBench — July 23, 2026
BenchLM mirrors the published score view for ZeroBench. GPT-5.4 leads the public snapshot at 41.0% , followed by Muse Spark (33.0%) and Gemini 3.1 Pro (29.0%). BenchLM does not use these results to rank models overall.
GPT-5.4
OpenAI
gpt-5-4
Muse Spark
Meta
muse-spark
Gemini 3.1 Pro
gemini-3-1-pro
Benchmark score table (4 models)
ScoreThe published ZeroBench snapshot places GPT-5.4 first at 41.0%. The third row is 12.0 points behind. The broader top-10 range is 18.0 points, so the table still separates the published systems.
4 models have been evaluated on ZeroBench. The benchmark falls in the Multimodal & Grounded category. This category carries a 12% weight in BenchLM.ai's overall scoring system. ZeroBench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About ZeroBench
Year
2026
Tasks
100 visual reasoning questions
Format
Multi-step visual reasoning
Difficulty
Tool-augmented visual reasoning
Meta evaluates ZeroBench on 100 main questions and reports pass@5, using an LLM judge to compare free-form answers against references. BenchLM stores it as a display-only multimodal reasoning benchmark.
BenchLM freshness & provenance
Version
ZeroBench 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
FAQ
What does ZeroBench measure?
A multi-step visual reasoning benchmark with pass@5 reporting and optional tool use.
Which model scores highest on ZeroBench?
GPT-5.4 by OpenAI currently leads with a score of 41.0% on ZeroBench.
How many models are evaluated on ZeroBench?
4 AI models have been evaluated on ZeroBench on BenchLM.
Compare Top Models on ZeroBench
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.