Public KG record
GLM-5.2
Recorded overview
Showed a small, statistically insignificant boost in the pelican-on-bicycle cell
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Benchmarks: BrowseComp和SpreadsheetBench结果混合
- Benchmarks: Terminal Bench v2.1 得分 81.0
- Benchmarks: Binary Exploitation benchmark
- Benchmarks: CyberGym
- Benchmarks: ExploitBench
- Benchmarks: ExploitGym
- Benchmarks: Pelican
- Benchmarks: Terminal-Bench 3.0
Evidence coverage
The KG currently records 12 known information dimensions and has 7 undocumented dimensions, linked to 32 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- Prime Agent — outperforms
- Baseten — integrates
- Baseten — supports
- NVIDIA — develops
- Zhipu AI / GLM — develops