Decision Workspace
miyabi-benchmark vs evalhub-schema vs sharpebench-core
Side-by-side comparison of Rust crates
35
miyabi-benchmark
experimentalv0.1.2
Benchmark evaluation for Miyabi - SWE-bench Pro, AgentBench, HAL, Galileo
58
evalhub-schema
experimentalv0.4.0
evalhub record types: the source of the JSON Schema and OpenAPI contract.
57
sharpebench-core
experimentalv0.28.0
Deterministic, luck-robust quantitative evaluation kernel for trading agents.
Core Metrics
| miyabi-benchmark | evalhub-schema | sharpebench-core | |
|---|---|---|---|
| Health Score | 35 | 58 | 57 |
| Total Downloads | 49 | 154 | 3.7K |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 16 | 297 |
| Releases | 1 | 8 | 48 |
| Last Updated | 322d ago | 12d ago | 21d ago |
| Age | 10m | 18d | 3m |
Health Breakdown
miyabi-benchmark
Maintenance
3
Quality
13
Community
5
Popularity
2
Documentation
12
evalhub-schema
Maintenance
18
Quality
13
Community
9
Popularity
3
Documentation
15
sharpebench-core
Maintenance
18
Quality
12
Community
13
Popularity
4
Documentation
10
Technical Details
| miyabi-benchmark | evalhub-schema | sharpebench-core | |
|---|---|---|---|
| Version | 0.1.2 | 0.4.0 | 0.28.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | Apache-2.0 | AGPL-3.0-only | MIT OR Apache-2.0 |
| Dependencies | 18 | 6 | 5 |
| Crate Size | 44KB | 65KB | 348KB |
| Features | 2 | 0 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2024 | 2021 |
| MSRV | 1.75.0 | 1.94 | — |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •evalhub-schema leads with a health score of 58/100, but none of the options score above 80.
- •sharpebench-core has the most downloads (3.7K), suggesting wider adoption.
- •sharpebench-core is depended on by 297 crates — strongest ecosystem trust.