mirror of
https://github.com/lukaszraczylo/llm-testbench.git
synced 2026-10-13 00:48:29 +00:00
lukaszraczylo
7264fe81b7
Both reviewers found evaluators that scored correct answers as zero: hardcoded flag order, quote-style rigidity, missing multiline anchors, comma-grouped numbers, ratio notation, and numeric strings in JSON. A shared ExactToken evaluator now normalizes fences, quotes, and trailing periods for exact-answer tests. The obsolete tmutil snapshot reference now accepts the current localsnapshot verb.
24 lines
673 B
Go
24 lines
673 B
Go
package tests
|
|
|
|
import "github.com/lukaszraczylo/llm-testbench/internal/testkit"
|
|
|
|
// All builds a Registry containing the full test catalog, spanning the
|
|
// programming (golang, python, typescript, c), operations (macos, linux,
|
|
// kubernetes), research (web, whitepapers, codebase), and agents
|
|
// (tool-routing, planning) categories.
|
|
func All() *testkit.Registry {
|
|
r := testkit.NewRegistry()
|
|
registerGolangTests(r)
|
|
registerPythonTests(r)
|
|
registerTypeScriptTests(r)
|
|
registerCTests(r)
|
|
registerMacOSTests(r)
|
|
registerLinuxTests(r)
|
|
registerKubernetesTests(r)
|
|
registerWebTests(r)
|
|
registerWhitepapersTests(r)
|
|
registerCodebaseTests(r)
|
|
registerAgentsTests(r)
|
|
return r
|
|
}
|