frontend development benchmark
Artifacts Bench
Artifacts Bench evaluates a model's ability to generate visual code artifacts, measuring the quality of generated interactive and visual front-end outputs from natural-language requests.
Updated Aug 7, 2026
Published models3
Registry coverage3
MetricScore
EvidenceB
Artifacts Bench leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | BY | 51.0% | 100.0% | 3 | C | |
| 2 | BY | 47.0% | 50.0% | 3 | C | |
| 3 | MI | 36.4% | 0.0% | 3 | C |
Score distribution
Top published rows on the benchmark's original scale.
Artifacts Bench highlights
The top published results on this benchmark's own scale.
What is Artifacts Bench?
Definition and scoring fields from the benchmark registry.
Artifacts Bench evaluates a model's ability to generate visual code artifacts, measuring the quality of generated interactive and visual front-end outputs from natural-language requests.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- Artifacts Bench
- Modality
- text
- Primary category
- frontend development
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- artifacts-bench|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about Artifacts Bench.
Which model scores highest on Artifacts Bench?
Seed 2.1 Pro is currently ranked first with 51.0%.
What does Artifacts Bench measure?
Artifacts Bench evaluates a model's ability to generate visual code artifacts, measuring the quality of generated interactive and visual front-end outputs from natural-language requests.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.