Loreon
Labs
Platform
Docs
Home
Ecosystems
Python
bench
taasaa/bench
Python
Emerging
GitHub
Stars
—
Forks
—
Contributors
1
Last push
4m ago
Recent commits
Latest commits.
Merge fix/multishot-usage-drop: multishot usage-drop fix + m3 cost reference
4549380
Michael Mazyar
15m ago
fix(costs): switch reference from m2.7 to m3 (resolves 08f19328)
7478db0
Michael Mazyar
31m ago
docs(results): m3 card consolidated after full multishot re-eval
6734d52
Michael Mazyar
2h ago
docs(results): m3 card auto-regenerated after u17 re-eval
fadd89e
Michael Mazyar
3h ago
fix(multishot): preserve usage + choices on tool-loop path (closes 4b4ad356)
32825c2
Michael Mazyar
3h ago
fix(costs): add reference_cost_usd for u17/u18 (closes 5e7bab13 data gap)
b6415ab
bench
4h ago
refactor(pricing): Y-invert resolver order; empty MODEL_ALIAS_MAP to catch-all role
5531f1b
bench
6h ago
Merge fix/recorded-name-proxy-stable-tests: proxy-stable invariant tests
cc38a29
Michael Mazyar
7h ago
Top contributors
Builders behind this project.
taasaa
163 commits