reasoning benchmark
FullStackBench zh
Chinese subset of FullStackBench for evaluating end-to-end software engineering and full-stack development capability.
Updated Aug 7, 2026
Published models3
Registry coverage3
MetricScore
EvidenceB
FullStackBench zh leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 58.7% | 100.0% | 3 | C | |
| 2 | AC | 57.4% | 50.0% | 3 | C | |
| 3 | AC | 55.0% | 0.0% | 3 | C |
Score distribution
Top published rows on the benchmark's original scale.
FullStackBench zh highlights
The top published results on this benchmark's own scale.
What is FullStackBench zh?
Definition and scoring fields from the benchmark registry.
Chinese subset of FullStackBench for evaluating end-to-end software engineering and full-stack development capability.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- FullStackBench zh
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- fullstackbench-zh|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about FullStackBench zh.
Which model scores highest on FullStackBench zh?
Qwen3.5-122B-A10B is currently ranked first with 58.7%.
What does FullStackBench zh measure?
Chinese subset of FullStackBench for evaluating end-to-end software engineering and full-stack development capability.
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.