mirror of
https://github.com/lukaszraczylo/llm-testbench.git
synced 2026-10-12 00:45:19 +00:00
lukaszraczylo
1d51d4cbbd
Framework runs a category/subcategory test catalog against multiple LLMs through an OpenAI-compatible endpoint. Deterministic evaluators score each response. Reports render as table, markdown, or JSON.
25 lines
747 B
Go
25 lines
747 B
Go
package tests
|
|
|
|
import "github.com/lukaszraczylo/llm-testbench/internal/testkit"
|
|
|
|
// All builds a Registry containing the full 17-test catalog: 3
|
|
// programming/golang, 2 programming/python, 1 programming/typescript, 1
|
|
// programming/c, 2 operations/macos, 2 operations/linux, 1
|
|
// operations/kubernetes, 1 research/web, 1 research/whitepapers, 1
|
|
// research/codebase, and 2 agents (tool-routing, planning).
|
|
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
|
|
}
|