Decision Workspace
evalcore vs adk-eval vs eval-core
Side-by-side comparison of Rust crates
49
evalcore
experimentalv0.7.5
Know when your AI gets worse before your users do. The eval engine for AI systems: record, replay, compare, and gate LLM and agent behavior
66
adk-eval
growingv2.3.0
Agent evaluation framework for ADK-Rust
54
eval-core
experimentalv0.4.0
A testing framework for LLM agents: prompt-based test cases with built-in assertions on tool calls, parameters, and text/math output — bring your own harness.
Core Metrics
| evalcore | adk-eval | eval-core | |
|---|---|---|---|
| Health Score | 49 | 66 | 54 |
| Total Downloads | 164 | 6.5K | 236 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 33 | 0 |
| Releases | 8 | 27 | 4 |
| Last Updated | 82d ago | today | 110d ago |
| Age | 2m | 10m | 3m |
Health Breakdown
evalcore
Maintenance
14
Quality
11
Community
6
Popularity
3
Documentation
15
adk-eval
Maintenance
20
Quality
17
Community
9
Popularity
5
Documentation
15
eval-core
Maintenance
18
Quality
12
Community
6
Popularity
3
Documentation
15
Technical Details
| evalcore | adk-eval | eval-core | |
|---|---|---|---|
| Version | 0.7.5 | 2.3.0 | 0.4.0 |
| Stable (≥1.0) | ✗ No | ✓ Yes | ✗ No |
| License | Apache-2.0 | Apache-2.0 | MIT OR Apache-2.0 |
| Dependencies | 16 | 23 | 11 |
| Crate Size | 49KB | 96KB | 81KB |
| Features | 0 | 6 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2024 | 2024 |
| MSRV | 1.75 | 1.95 | 1.88 |
| 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.
- •evalcore, eval-core are pre-1.0 — API may change.