Model Profile
GLM-5
Use this page to decide where this model is a strong fit. Rankings below are benchmark-backed by use case, with explicit confidence and contributor metrics.
Identity
ID: zai-org/GLM-5
Author: zai-org
Origin: huggingface_catalog
Arch: unknown
Benchmark Coverage
Scored use cases: 12
Avg confidence: 23.4%
Evidence points: 168
Raw rows: 166
Weighted rows: 31
Catalog Metadata
Parameters: unknown
Context window: 4096
Downloads: 166,549
Intelligence Profile
Dimension Breakdown
No eq benchmarks found
No accuracy benchmarks found
* Low confidence — limited benchmark evidence for this dimension
3/5 dimensions scored · Last updated Apr 21, 2026
Benchmark Signals
Click through to the benchmark source behind this model profile.
Sonar Java Quality Leaderboard
functional_skill_pct
Normalized value 89.6% · confidence 100.0%
Strongest impact in Code Review Assistant
sonar_java_quality.functional_skill_pct · Apr 1, 2026
Sonar Java Quality Leaderboard
issue_density_error_per_kloc
Normalized value 100.0% · confidence 100.0%
Strongest impact in Code Review Assistant
sonar_java_quality.issue_density_error_per_kloc · Apr 1, 2026
OpenHands Issue Resolution
issue_resolution_score_pct
Normalized value 59.0% · confidence 100.0%
Strongest impact in Agentic bug fixing
openhands_issue_resolution.issue_resolution_score_pct · Apr 1, 2026
OpenHands Index
issue_resolution_score_pct
Normalized value 59.0% · confidence 100.0%
Strongest impact in CAD scripting helper
openhands_index.issue_resolution_score_pct · Apr 1, 2026
OpenHands Index
average_score_pct
Normalized value 36.5% · confidence 100.0%
Strongest impact in Autonomous Coding Agent
openhands_index.average_score_pct · Apr 1, 2026
Sonar Java Quality Leaderboard
vulnerability_density_error_per_kloc
Normalized value 89.5% · confidence 100.0%
Strongest impact in Code generation
sonar_java_quality.vulnerability_density_error_per_kloc · Apr 1, 2026
Some fit rows have limited benchmark evidence.
6 of 12 scored use cases have low confidence or thin contributor coverage.
Coverage Diagnostics
actively scoredUse-Case Scores
24
Total Measurements
166
Weighted Measurements
31
Weighted Sources
10
Raw Source Coverage
Weighted Source Coverage
Best Use Cases for This Model
| Use Case | Score |
|---|---|
| Code generation use_case.dev.code_generation | 19.8% |
| CAD scripting helper use_case.eng.cad_scripting_helper | 18.2% |
| Agentic bug fixing use_case.dev.agentic_bug_fixing | 18.0% |
| IDE code completion use_case.dev.ide_completion | 17.6% |
| PR review agent use_case.dev.pr_review_agent | 17.5% |
| Autonomous Coding Agent use_case.dev.autonomous_coding_agent | 15.9% |
| Quant research code generation use_case.fin.alpha_research_codegen | 14.9% |
| Code Review Assistant use_case.dev.code_review_assistant | 14.0% |
| Function Calling / Tool Use Agent use_case.dev.function_calling_agent | 13.4% |
| Refactoring assistant use_case.dev.refactoring | 13.3% |
| Debugging assistant use_case.dev.debugging | 12.7% |
| Verilog/VHDL generation use_case.eda.verilog_generation | 12.4% |