Skip to content

Models Benchmarks Providers

Search models and benchmarks /

FullStackBench zh

coding

Categories: agents, code, reasoning
Modality: text
Language: zh
Multilingual: No
Max score: 1
Scoring: %, higher is better
Verified by llm-stats: No

Chinese subset of FullStackBench for evaluating end-to-end software engineering and full-stack development capability.

Leaderboard

Showing 3 of 3 results

Qwen3.5-122B-A10B

58.7%

i
Qwen3.5-27B

57.4%

i
Qwen3.5-35B-A3B

55.0%

i

Wikibench About Theme Content licensed CC BY-SA 4.0.