agents benchmark
Web Bench
Web Bench evaluates agents on realistic web-development engineering tasks, measuring end-to-end implementation in browser-based workflows.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
Web Bench Ranking
Higher score ranks better on this benchmark.
| 01 | BY | 78.4% | 100.0% | 2 | C | |
| 02 | BY | 73.6% | 0.0% | 2 | C |
Web Bench Score Distribution
A closer view of the leading scores on this benchmark.
Web Bench Highlights
The leading models and scores on this benchmark.
What is Web Bench?
What Web Bench measures and how its scores work.
Web Bench evaluates agents on realistic web-development engineering tasks, measuring end-to-end implementation in browser-based workflows.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Web Bench
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- web-bench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Web Bench.
Which model scores highest on Web Bench?
Seed 2.1 Pro is currently ranked first with 78.4%.
What does Web Bench measure?
Web Bench evaluates agents on realistic web-development engineering tasks, measuring end-to-end implementation in browser-based workflows.
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.