Data & Environment · Coding

Repository-level coding tasks in runnable environments.

Each task combines a work-ticket instruction, a pinned repository or seeded workspace, an executable test suite, and a reference solution. The submitted artifact receives a binary result under the task's verifier.

Executable environments Hidden tests Binary reward, no partial credit Terminal-Bench to DeepSWE
Task structure

Instruction, environment, tests, and reference solution.

Difficulty runs from Terminal-Bench-style self-contained work, where fixtures are seeded and the agent builds the tool an in-environment verifier then checks, to DeepSWE-style repository maintenance, where the agent patches a pinned revision of a real upstream project and the submitted patch is replayed against hidden tests in a separate image.

01

Instruction. Agent-facing, written as a ticket: required interface, the edge cases that matter, explicit definition of done.

02

Environment. A Docker image with the pinned repo or seeded fixtures, the toolchain, and declared CPU, memory and timeout limits.

03

Hidden tests. Never shown to the agent, so a solution cannot be written to the tests. They cover variants the seeded fixture does not.

04

Reference solution. A patch a maintainer would accept. It must score 1, and an empty submission must score 0, before the task ships.

Sample data

Eight tasks you can download and run.

A sample, not the catalog: systems-level work in Rust, Go and Python covering parser state machines, protocol recovery, binary reverse engineering, and vision-to-structure extraction. Each download contains the runnable task, its verifier, reference answer, and instructions for running it. Prior runs, provenance records, and identifying metadata are omitted.

TaskAreaRuntimeVerification
serde-json-sequenceRecoverable RFC 7464 JSON sequence parsingRustPatch-replay, separate image Download
chi-route-resolutionHTTP radix-tree route resolutionGoPatch-replay + race checks Download
wsproto-extension-transactionWebSocket extension parsing, transactional negotiationPythonPatch-replay, separate image Download
elf-note-calibration-repairELF note reverse engineering and binary repairPythonIn-environment verifier Download
greenhouse-frame-roundtripUndocumented binary frame decoding and encodingPython 3.11In-env + black-box probe Download
warmboot-config-fragment-recoveryCorrupted key/value page recoveryPythonIn-environment verifier Download
plotter-preview-motion-reportPPM parsing, HUD recognition, motion reconstructionPythonIn-environment verifier Download
route-sheet-graph-recoveryImage consensus and semantic graph extractionPythonIn-environment verifier Download

Run the whole set

Requires Docker and Harbor 0.21.0 or a compatible release. One task runs the same way, by pointing at its directory.

190 KB · 8 tasks · environments, verifiers and reference answers

harbor run \
  -p ./tasks \
  -a YOUR_AGENT \
  -m YOUR_MODEL \
  -o ./out -y
More data families