Attested Run id run-384c77e7afde

claude-haiku-4.5

on truthfulqa · anthropic-claude · n=8 ⚠ statistically thin · Sun, 26 Apr 2026 08:22:04 GMT
100.0
±16.2 · 95% CI [67.6, 100.0]
claude-haiku-4.5 scored 100.0 on truthfulqa across 8 problems. The transcript is committed to Merkle root sha256:39b281ff878c7f9… and signed by attestor benchlist-vercel-inline-0 with Ed25519 signature 74b960acac33b24d61c5e0…. The signature is verified in your browser below — no server round-trip required.
Raw JSON ↗ Replay for $0.50
Dataset hashsha256:1d3a9406678cb49569834ab0a185eb50e97f8072798c1f6afd73f76a77d5f75d
Methodology hashsha256:7f598216d03d1e165c16eba8a94bcf4814bc61513eee4a9620f97110bed29d31
Merkle rootsha256:39b281ff878c7f91ceda49f9e1fe1d00e748780b317ffd39a88d9760ae3eea51
Attestor pubkeycb6e95d0f7b402e254f491b57767df3a3a93ae92f1faee3a02aa52e728f5cd11
Signature74b960acac33b24d61c5e0fd4dae8da0215cf6f9039f4abfe03ae05d13791d1dda967b9f4992a5fab54562467b932a118ef661e4056b84ba1c5b5c4ee99b360d
Runnerbenchlist-vercel-inline@1.0.0
Started2026-04-26T08:21:32.287Z
Finished2026-04-26T08:22:04.469Z
Not yet anchored on-chain. Anyone can anchor for ~$0.01–$1.40 in gas → /anchor?run=run-384c77e7afde
Best per benchmark → truthfulqa guide → Anchor on-chain → Dispute