multimodal benchmark
ZEROBench Leaderboard
ZEROBench is a multimodal vision benchmark for zero-shot visual understanding tasks.
Updated Sep 5, 2026
Models10
Model coverage10
MetricScore
EvidenceB
ZEROBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMA | Score0.41 points | Percentile100.00% | Participants10 | EvidenceC | Evaluated |
| Rank02 | ModelDE | Score0.35 points | Percentile88.89% | Participants10 | EvidenceC | Evaluated |
| Rank03 | ModelME | Score0.33 points | Percentile77.78% | Participants10 | EvidenceC | Evaluated |
| Rank04 | ModelBY | Score0.18 points | Percentile66.67% | Participants10 | EvidenceC | Evaluated |
| Rank05 | ModelMA | Score0.11 points | Percentile55.56% | Participants10 | EvidenceC | Evaluated |
| Rank06 | ModelBY | Score0.11 points | Percentile44.44% | Participants10 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score0.10 points | Percentile33.33% | Participants10 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score0.09 points | Percentile22.22% | Participants10 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score0.08 points | Percentile11.11% | Participants10 | EvidenceC | Evaluated |
| Rank10 | ModelAC | Score0.04 points | Percentile0.00% | Participants10 | EvidenceC | Evaluated |
ZEROBench Highlights
The leading models and scores on this benchmark.
ZEROBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for ZEROBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is ZEROBench?
What ZEROBench measures and how its scores work.
ZEROBench is a vision benchmark designed to test models on zero-shot visual understanding tasks.
ZEROBench measures performance on zero-shot visual understanding tasks using a Score reported in points.
Scores are shown in points. This benchmark is not independently verified and has an evidence level of B.
- Family
- ZEROBench
- Modality
- image
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about ZEROBench.
Which model scores highest on ZEROBench?
Kimi K3 is currently ranked first with 0.41 points.
What are the top three models on ZEROBench?
The current leaders are Kimi K3 (0.41 points), DeepSeek-V4-Flash-Vision-Exp (0.35 points), and Muse Spark (0.33 points).
Which ZEROBench model has the lowest official input price?
DeepSeek-V4-Flash-Vision-Exp has the lowest matched official input price at $0.14 input / $0.28 output per 1M tokens.
Which models are fastest among ZEROBench results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.