Decision Workspace
rskit-bench vs vtcode-eval vs metrics-lib
Side-by-side comparison of Rust crates
56
rskit-bench
experimentalv0.2.0-alpha.5
ML benchmarking framework: evaluators, metrics, reports, visualization
60
vtcode-eval
experimentalv0.175.1
Agent evaluation framework for VT Code: pass@k / pass^k metrics, capability and regression evals, and environment-based outcome verification.
59
metrics-lib
stablev1.0.0
High-performance Rust metrics library: sub-2ns counters, sub-1ns gauges, nanosecond timers, tumbling-window rate meters, async timing, adaptive sampling, and system health. Cross-platform with minimal dependencies.
Core Metrics
| rskit-bench | vtcode-eval | metrics-lib | |
|---|---|---|---|
| Health Score | 56 | 60 | 59 |
| Total Downloads | 161 | 3.1K | 36.5K |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 12 | 115 | 19 |
| Releases | 6 | 126 | 12 |
| Last Updated | 54d ago | 1d ago | 144d ago |
| Age | 3m | 2m | 1y 1m |
Health Breakdown
rskit-bench
Maintenance
19
Quality
11
Community
8
Popularity
3
Documentation
15
vtcode-eval
Maintenance
17
Quality
13
Community
11
Popularity
4
Documentation
15
metrics-lib
Maintenance
12
Quality
17
Community
10
Popularity
5
Documentation
15
Technical Details
| rskit-bench | vtcode-eval | metrics-lib | |
|---|---|---|---|
| Version | 0.2.0-alpha.5 | 0.175.1 | 1.0.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✓ Yes |
| License | MIT | MIT OR Apache-2.0 | Apache-2.0 |
| Dependencies | 19 | 7 | 19 |
| Crate Size | 63KB | 31KB | 218KB |
| Features | 0 | 0 | 17 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2024 | 2024 | 2021 |
| MSRV | 1.91 | 1.98.1 | 1.70 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •vtcode-eval leads with a health score of 60/100, but none of the options score above 80.
- •metrics-lib has the most downloads (36.5K), suggesting wider adoption.
- •vtcode-eval is depended on by 115 crates — strongest ecosystem trust.
- •rskit-bench, vtcode-eval are pre-1.0 — API may change.