Decision Workspace
prompt-eval-rubric vs agentforge-scorer vs adk-eval
Side-by-side comparison of Rust crates
42
prompt-eval-rubric
experimentalv0.1.0
Score LLM outputs against named 0.0-1.0 rubrics. Rubrics rank; validators reject. Weighted aggregation, exception-isolated scoring.
39
agentforge-scorer
experimentalv0.1.10
Trace analyzer and scorer (F-04): deterministic assertions, LLM-as-judge, failure clustering
66
adk-eval
growingv2.3.0
Agent evaluation framework for ADK-Rust
Core Metrics
| prompt-eval-rubric | agentforge-scorer | adk-eval | |
|---|---|---|---|
| Health Score | 42 | 39 | 66 |
| Total Downloads | 22 | 304 | 6.5K |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 6 | 33 |
| Releases | 1 | 1 | 27 |
| Last Updated | 138d ago | 134d ago | today |
| Age | 4m | 4m | 10m |
Health Breakdown
prompt-eval-rubric
Maintenance
6
Quality
14
Community
5
Popularity
2
Documentation
15
agentforge-scorer
Maintenance
7
Quality
11
Community
8
Popularity
3
Documentation
10
adk-eval
Maintenance
20
Quality
17
Community
9
Popularity
5
Documentation
15
Technical Details
| prompt-eval-rubric | agentforge-scorer | adk-eval | |
|---|---|---|---|
| Version | 0.1.0 | 0.1.10 | 2.3.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✓ Yes |
| License | MIT OR Apache-2.0 | MIT | Apache-2.0 |
| Dependencies | 2 | 18 | 23 |
| Crate Size | 10KB | 35KB | 96KB |
| Features | 0 | 0 | 6 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2024 |
| MSRV | 1.74 | — | 1.95 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •adk-eval leads with a health score of 66/100, but none of the options score above 80.
- •prompt-eval-rubric, agentforge-scorer are pre-1.0 — API may change.