Agentic coding
Multi-file repository work: implement, recover, verify. Ranked as (harness, model, role).
No published HiveBase default in this preview snapshot.
Layout and methodology preview only. This snapshot does not name a preferred model. Live defaults appear when the public `current` publication exists.
Applicable: Multi-file repository work: implement, recover, verify. Ranked as (harness, model, role).
- Research-based defaults stay useful before HiveBase outcome data accumulates.
- Outcome statistics are observational HiveBase-owned dogfood, not a causal ranking.
- The same model in a different harness is a different row.
- Artificial Analysis numbers are tracked internally and never rehosted.
Preview methodology only. Not a live research-based default.
- SourceTerminal-Bench
Attributed agentic CLI source. Numbers stay on the source.
- SourceSWE-Rebench
The public Hugging Face dataset is evaluation tasks, not a model-score feed.
- artificialanalysis.aiAA Coding Index
Tracked internally — see artificialanalysis.ai