agents benchmark
Trae Code Gen
Trae Code Gen is a component of Trae Agent Bench that evaluates implementing new functionality across multiple programming languages in containerized, runnable repositories.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
Trae Code Gen leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | BY | 62.4% | 100.0% | 2 | C | |
| 2 | BY | 59.7% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
Trae Code Gen highlights
The top published results on this benchmark's own scale.
What is Trae Code Gen?
Definition and scoring fields from the benchmark registry.
Trae Code Gen is a component of Trae Agent Bench that evaluates implementing new functionality across multiple programming languages in containerized, runnable repositories.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- Trae Code Gen
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- trae-code-gen|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about Trae Code Gen.
Which model scores highest on Trae Code Gen?
Seed 2.1 Pro is currently ranked first with 62.4%.
What does Trae Code Gen measure?
Trae Code Gen is a component of Trae Agent Bench that evaluates implementing new functionality across multiple programming languages in containerized, runnable repositories.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 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.