{"id":"run-90f62a5afcfb","serviceId":"anthropic-claude","benchmarkId":"gsm8k","model":"claude-haiku-4-5","score":100,"runs":1,"breakdown":{"n":8,"passes":8,"mean_raw":1},"sampleCount":8,"runnerVersion":"benchlist-vercel-inline@1.0.0","runnerCommit":"edge","datasetHash":"sha256:09a35a0a0a48f13840457c82e2c2da6a7884ec21b51154139867843c2e4da5c7","methodologyHash":"sha256:144e8efdcdb66a248c57935cea7c8d00cbc6c287341355ab753cc5f445238bfb","transcriptMerkleRoot":"sha256:4d7cc7ff5b489d00aee230a9a89ab3d2aca91bd38b7e16f297e7e8a3d8c035d1","startedAt":"2026-04-26T19:26:02.768Z","finishedAt":"2026-04-26T19:26:15.228Z","durationSeconds":12,"decoding":{"temperature":0,"max_tokens":512},"attestor":"benchlist-vercel-inline-0","runner_provenance":{"runner_version":"benchlist-vercel-inline@1.0.0","runner_commit":"3b3562b5a0ff421dfb1530aaef628667a31dbd93","runner_repo":"github.com/benchlist/runner","adapter_hash":"sha256:inline-js:gsm8k","judge_hash":"sha256:inline-js:scoreOne","lockfile_hash":null,"system_prompt_hash":null,"chat_template_hash":"sha256:inline-js:default","decoding":{"temperature":0,"max_tokens":512,"tier":"easy"},"digest":"sha256:7e9f1dfe479c7831a6b11092144a02bab7c52861802c40dbca2faeaec47a46d1"},"publisher":"anthropic-claude","replay":{"command":"benchlist run gsm8k --service anthropic-claude --model claude-haiku-4-5 --runs 1 --limit 8","dockerImage":"ghcr.io/benchlist/runner:latest","envRequired":[]},"proof":{"system":"signed-attestation","status":"signed","signature":"03fee5c994a957a3cdcea5195327666f03d4fef685bf1fb6d5ddcbf840db416e8d7d15c02e6b5256afc04b68fade73a6594b071e1e0699087868183d6d50dc06","pubkey":"cb6e95d0f7b402e254f491b57767df3a3a93ae92f1faee3a02aa52e728f5cd11","signer_algo":"ed25519","public_inputs":{"dataset_hash":"sha256:09a35a0a0a48f13840457c82e2c2da6a7884ec21b51154139867843c2e4da5c7","methodology_hash":"sha256:144e8efdcdb66a248c57935cea7c8d00cbc6c287341355ab753cc5f445238bfb","merkle_root":"sha256:4d7cc7ff5b489d00aee230a9a89ab3d2aca91bd38b7e16f297e7e8a3d8c035d1","claimed_score":100,"runner_provenance":"sha256:7e9f1dfe479c7831a6b11092144a02bab7c52861802c40dbca2faeaec47a46d1"}},"verification":{"mode":"signed-attestation","status":"attested","alignedProofSystem":"signed-attestation","attestorPubkey":"cb6e95d0f7b402e254f491b57767df3a3a93ae92f1faee3a02aa52e728f5cd11","attestorSignature":"03fee5c994a957a3cdcea5195327666f03d4fef685bf1fb6d5ddcbf840db416e8d7d15c02e6b5256afc04b68fade73a6594b071e1e0699087868183d6d50dc06","signerAlgo":"ed25519","submittedAt":"2026-04-26T19:26:15.228Z","verifiedAt":"2026-04-26T19:26:15.228Z","note":"Signed inline by Benchlist Vercel attestor. Set ATTESTOR_PRIVATE_KEY on a GH/Railway worker to add Ethereum L1 anchor."}}