reasoning benchmark
CreativeWork
CreativeWork evaluates agents on open-ended creative production tasks within realistic tool and application environments, measuring the quality and completeness of generated deliverables.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
CreativeWork Ranking
Higher score ranks better on this benchmark.
| 1 | BY | 42.5% | 100.0% | 2 | C | |
| 2 | BY | 34.5% | 0.0% | 2 | C |
CreativeWork Score Distribution
A closer view of the leading scores on this benchmark.
CreativeWork Highlights
The leading models and scores on this benchmark.
What is CreativeWork?
What CreativeWork measures and how its scores work.
CreativeWork evaluates agents on open-ended creative production tasks within realistic tool and application environments, measuring the quality and completeness of generated deliverables.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- CreativeWork
- Modality
- multimodal
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- creativework|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about CreativeWork.
Which model scores highest on CreativeWork?
Seed 2.1 Pro is currently ranked first with 42.5%.
What does CreativeWork measure?
CreativeWork evaluates agents on open-ended creative production tasks within realistic tool and application environments, measuring the quality and completeness of generated deliverables.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.