Decision Workspace
miyabi-benchmark vs serdes-ai-evals vs recallbench
Side-by-side comparison of Rust crates
39
miyabi-benchmark
experimentalv0.1.2
Benchmark evaluation for Miyabi - SWE-bench Pro, AgentBench, HAL, Galileo
48
serdes-ai-evals
experimentalv0.2.6
Evaluation framework for testing and benchmarking serdes-ai agents
46
recallbench
experimentalv0.4.0
A universal benchmark harness for AI memory systems
Core Metrics
| miyabi-benchmark | serdes-ai-evals | recallbench | |
|---|---|---|---|
| Health Score | 39 | 48 | 46 |
| Total Downloads | 40 | 399 | 55 |
| 30d Downloads | 4 | 105 | 55 |
| Dependents | 0 | 8 | 0 |
| Releases | 1 | 10 | 5 |
| Last Updated | 125d ago | 35d ago | 6d ago |
| Age | 4m | 2m | 7d |
Health Breakdown
miyabi-benchmark
Maintenance
7
Quality
13
Community
5
Popularity
2
Documentation
12
serdes-ai-evals
Maintenance
11
Quality
14
Community
8
Popularity
3
Documentation
12
recallbench
Maintenance
19
Quality
10
Community
5
Popularity
2
Documentation
10
Technical Details
| miyabi-benchmark | serdes-ai-evals | recallbench | |
|---|---|---|---|
| Version | 0.1.2 | 0.2.6 | 0.4.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | Apache-2.0 | MIT | MIT OR Apache-2.0 |
| Dependencies | 18 | 15 | 24 |
| Crate Size | 44KB | 29KB | 266KB |
| Features | 2 | 2 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2024 |
| MSRV | 1.75.0 | 1.75.0 | — |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •serdes-ai-evals leads with a health score of 48/100, but none of the options score above 80.