runebench/skill-xp
Skill progression
Accumulate measurable skill experience within a fixed episode.
RuneScape SDKMCP control
Not yet importedRequires sandbox
RuneBench
Upstream publisher Max BittkerMaxBittker/runebench
Coding-agent tasks inside an emulated RuneScape world, scored by skill progression and resource collection over fixed time windows.
simulationcoding-agentsgamessandbox
PROVENANCEUPSTREAM RECORD
- Upstream source
- MaxBittker/runebench
- Trunchbull port
- Not packaged
- Version
- UPSTREAM
- Release digest
- Not compiled
- License
- Review required
Source commit: Upstream head not pinnedPublished Indexed July 30, 2026
WHAT THIS PROJECT MEASURES
README
RuneBench asks agents to write and execute TypeScript against a RuneScape SDK and MCP control surface. Numeric rewards and time-series progress are part of the benchmark, not optional telemetry.
A faithful Trunchbull import requires longer sandbox leases, deterministic world resets, readiness checks, SDK/MCP tools, concurrent trials, and durable score and video artifacts.
EXECUTION CONTRACT
Requires a stateful game sandbox, SDK/MCP control, 20–40 minute leases, numeric rewards, and clean resets.
TRUNCHBULL AVAILABILITY
Import status
Not yet imported
Not yet imported. This is the recommended first simulation-center integration, but it requires production-quality lifecycle and scoring work.
2 CASES
Evaluation cases
2
Requires sandbox
runebench/gold
Gold collection
Plan and execute a resource strategy against a numeric reward.
RuneScape SDKMCP control
2 REQUESTED TOOLS
Tools
2
RuneScape SDK
sandboxStructured observations and actions for the emulated game world.
Required
MCP control
sandboxExposes the benchmark's agent-control interface inside the lease.
Required
MACHINE-READABLE PROVENANCE
Registry record
{
"name": "RuneBench",
"catalogOwner": null,
"source": {
"url": "https://github.com/MaxBittker/runebench",
"version": "Upstream project",
"commit": "Upstream head not pinned",
"license": "Review required"
},
"port": null,
"release": {
"digest": "Not compiled",
"lane": "sandbox",
"sandboxRequired": true
},
"cases": [
"runebench/skill-xp",
"runebench/gold"
],
"tools": [
"RuneScape SDK",
"MCP control"
]
}BUILD ON THIS PROJECT