Skip to main content

Benchmark profile

ZeroBench

A multi-step visual reasoning benchmark with pass@5 reporting and optional tool use.

Data verified

Benchmark 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.

4 modelsMultimodal & GroundedCurrentDisplay onlyUpdated July 23, 2026

Benchmark score table (4 models)

Score
1
GPT-5.4OpenAI · Closed
41.0%
2
Muse SparkMeta · Closed
33.0%
3
Gemini 3.1 ProGoogle · Closed
29.0%
4
Kimi K3Moonshot AI · Closed
23.0%

The 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

CurrentDisplay only

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.

Last updated: July 23, 2026 · BenchLM version ZeroBench 2026

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.