Multimodal & Grounded benchmark
ZeroBench leaderboard
Every model the catalog carries a published ZeroBench value for, ranked by that value.
CategoryMultimodal & Grounded
MeasureMulti-step visual reasoning
Tasks100 visual reasoning questions
DifficultyTool-augmented visual reasoning
Published byMuse Spark Eval Methodology
A multi-step visual reasoning benchmark with pass@5 reporting and optional tool use.
ZeroBench ranking
8 models with a published ZeroBench value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Multi-step visual reasoning |
|---|---|---|---|
| 1 |  GPT-5.4 | OpenAI | 41.0 |
| 2 |  Muse Spark | Meta | 33.0 |
| 3 |  Gemini 3.1 Pro | 29.0 | |
| 4 |  Qwen3.8 Max | Alibaba | 24.0 |
| 5 |  Kimi K3 | Moonshot AI | 23.0 |
| 6 | DSdots3-note Preview | Dots Studio | 19.0 |
| 7 |  Seed 2.1 Pro | ByteDance | 18.0 |
| 8 | Seed 2.1 Turbo | ByteDance | 11.0 |
Evidence key: Observed
Rows are ordered by the value Muse Spark Eval Methodology published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.