← Leaderboard

Verifier card — reward_bench · grade ERR

Not auditable under the harness image — an env-compatibility signal, NOT a passing grade.

Not auditable

ConnectionError: Couldn't reach 'allenai/reward-bench' on the Hub (OfflineModeIsEnabled)

How to fix: Likely a dataset-at-load env — pre-fetch its dataset with --hf-dataset <id> so it loads offline (run once with any cached dataset; the error names the real id).

Audit your environment

Shipping a verifiers-format environment? We run this exact deterministic, model-free audit — gaming & difficulty — and hand back a sealed, replayable verifier card your buyers re-run themselves. No trust required.

Self-serve on the certification gateway at api.s2ar.dev — every seal on this board re-verifies free at /v1/verify/<record_sha256>, no account.

Audit your environment →