The Most Annoying AI Benchmark

EVIDENCE JSON

Proof you can inspect.

One week after each completed test, we publish a JSON bundle with challenge questions, exact prompts, recorded responses, judge reasons, and receipts.

  1. Live list

    The leaderboard page shows pending and available bundles with a live release countdown.

  2. Archive endpoint

    /v1/benchmarks/evidence-archives lists public bundles and their release times.

  3. Download endpoint

    /v1/benchmarks/evidence-archives/{run_id}.json downloads an available bundle.

GET /v1/benchmarks/evidence-archives

What GavelTM makes public

  1. Evidence bundle

    Frozen prompts, recorded model replies, expected outputs, judge reasons, and receipt references are released on the public schedule.

  2. Replay boundary

    Hashes identify the canonical evidence object. A matching hash means the released JSON has not silently changed.

  3. Claim ceiling

    The public claim is limited to this benchmark pack. GenXis does not expose private authoring machinery or use it as a substitute for public evidence.

Audit this evidence pack in:

PerplexityGeminiClaudeGrokChatGPT