Attested Run id run-71345cab5274

claude-haiku-4.5

on mmlu · anthropic-claude · n=8 ⚠ statistically thin · Sun, 26 Apr 2026 08:38:10 GMT
87.5
±22.4 · 95% CI [52.9, 97.8]
claude-haiku-4.5 scored 87.5 on mmlu across 8 problems. The transcript is committed to Merkle root sha256:6a06687deb4e771… and signed by attestor benchlist-vercel-inline-0 with Ed25519 signature 3472ab4b892ec00c3309b3…. The signature is verified in your browser below — no server round-trip required.
Raw JSON ↗ Replay for $0.50
Dataset hashsha256:05ef744f592cd2481092a6ecdecbccaf5e515f6ac2be7d5fc77ad85b8165f15c
Methodology hashsha256:f65dba1e549ab81ea004be624791ae7b7b3e784648c0cb2ce84b8bf930bb0457
Merkle rootsha256:6a06687deb4e771ef77943cde919002b8d27b27ab6ce8d20cef1bdeced61dbd4
Attestor pubkeycb6e95d0f7b402e254f491b57767df3a3a93ae92f1faee3a02aa52e728f5cd11
Signature3472ab4b892ec00c3309b3e73fc456e6366d8a5f7f544f94425c7a1614bdf12bb7c0b11ec3623188aa5b9589db7db2de183c14d57e5236868e819a5479b30706
Runnerbenchlist-vercel-inline@1.0.0
Started2026-04-26T08:37:36.799Z
Finished2026-04-26T08:38:10.075Z
Not yet anchored on-chain. Anyone can anchor for ~$0.01–$1.40 in gas → /anchor?run=run-71345cab5274
Best per benchmark → mmlu guide → Anchor on-chain → Dispute