The open arena for post‑training
Contribute an RL environment. We post-train a model on it and score what generalizes across eight domains.
Most competitions fix the environment and ask you to submit an agent. We invert that contract.
You contribute environments; we post-train a model on them and evaluate what holds up everywhere else. Frontier labs post-train on more than a million RL environments. The open community has roughly a thousand — at far lower quality, and largely confined to coding. PostTrain Arena closes that gap across eight under-served domains.
Contribute
A self-contained task package: task.md plus an environment, verifier and oracle.
Post-train
We run a Qwen3-8B model through a managed pipeline on your environment — no GPUs or API keys from you.
Score
We evaluate on BenchFlow Signals, a private held-out suite where no domain exceeds 20% of tasks.
Rank
By held-out generalization over a baseline, on tasks your environment cannot have memorized.
Built by the team behind SkillsBench
SkillsBench — the most-cited new agentic, diverse-domain benchmark of 2026 — drew roughly 100 citations in four months; the CAIS Agent Skills workshop drew 103 submissions. Co-organizer Kyoung Whan Choe authored PufferLib, the most-used non-LLM RL library. A 1,100-member community is already building in the open.
Organizer Dawn Song co-directs Berkeley RDI, whose AgentBeats hub runs live, reproducible agent-benchmark leaderboards — its benchmarks are surfaced in the catalog.
What a submission contains
A self-contained task package. Everything accepted is released openly.
task.mdYAML frontmatter for limits and metadata; Markdown body for the prompt, with optional multi-scene / multi-role structure.environment/A Docker image that runs the task deterministically, with pinned dependencies and no network egress.verifier.pyScores an attempt from final state, not from the transcript. Must be robust to reward hacking.oracle/A reference solution that proves the task is solvable inside the stated limits.