Attested Run id run-humaneval-05028db448

claude-sonnet-4-5-20250929

on humaneval · anthropic-claude · n=20 ⚠ statistically thin · Fri, 24 Apr 2026 20:42:43 GMT
91.5
±13.0 · 95% CI [71.8, 97.9]
claude-sonnet-4-5-20250929 scored 91.5 on humaneval across 20 problems. The transcript is committed to Merkle root sha256:c4a5bcffffaafe3… and signed by attestor benchlist-runner-0 with Ed25519 signature 4b9acd6c4daa21b49ccd14…. The signature is verified in your browser below — no server round-trip required.
Raw JSON ↗ Replay for $0.50
Dataset hashsha256:3e1eb278fb45e71a150b896866387eae8c5bf42c0618c1a543fd5bb03cd3edaf
Methodology hashsha256:ce08d4538a6db120acb39fa9c8102cd61be51040a3cc735f9be0952fe445a1db
Merkle rootsha256:c4a5bcffffaafe3332c77da6ed476ee80564b0a4c5a9aaf461be579fdcd0c501
Attestor pubkeyf38712fae5f11a2fc2fe3f7541264f04cd90974affdf1cce05163ecdaf35d457
Signature4b9acd6c4daa21b49ccd14b1c660ec389841cc1fb901ee4709fe32bce664bef947d2a1df04faf45245fc7a19a23515d208a9908597f5d9d39bcd63373cb00c0d
Runnerbenchlist-runner@1.0.0
Started2026-04-24T20:40:43Z
Finished2026-04-24T20:42:43Z
Not yet anchored on-chain. Anyone can anchor for ~$0.01–$1.40 in gas → /anchor?run=run-humaneval-05028db448
Best per benchmark → humaneval guide → Anchor on-chain → Dispute