Attested Run id run-6deacb1f549a

claude-haiku-4.5

on mmlu-pro · anthropic-claude · n=8 ⚠ statistically thin · Sun, 26 Apr 2026 07:49:10 GMT
50.0
±28.5 · 95% CI [21.5, 78.5]
claude-haiku-4.5 scored 50.0 on mmlu-pro across 8 problems. The transcript is committed to Merkle root sha256:de2ce627d5ed424… and signed by attestor benchlist-vercel-inline-0 with Ed25519 signature e5e95f9ba975394397a100…. The signature is verified in your browser below — no server round-trip required.
Raw JSON ↗ Replay for $0.50
Dataset hashsha256:f83f7230d012b45f7532fd0947ca596e7de52a518e7f9edcd0df4566b409bf9a
Methodology hashsha256:7d4179c2b699af35bc95f0bd466e9b344ae348a765fbbca15e14adbc4ceb7072
Merkle rootsha256:de2ce627d5ed4249245ecdfbe03ec92f6449526f1dc189c8dcd578cc6789e2e9
Attestor pubkeycb6e95d0f7b402e254f491b57767df3a3a93ae92f1faee3a02aa52e728f5cd11
Signaturee5e95f9ba975394397a1007ca794d09f4d9b4f4cb1da5d05878e09fefd1ac14375b9480e2b85dc1bfb0ff6663e147c9232788e4ba1d86638beaa6aeed45d250d
Runnerbenchlist-vercel-inline@1.0.0
Started2026-04-26T07:43:24.972Z
Finished2026-04-26T07:49:10.937Z
Not yet anchored on-chain. Anyone can anchor for ~$0.01–$1.40 in gas → /anchor?run=run-6deacb1f549a
Best per benchmark → mmlu-pro guide → Anchor on-chain → Dispute