Which model leads Humanity's Last Exam (w/ tools)?

Q: Which model leads Humanity's Last Exam (w/ tools)?

Claude Opus 5.5 tops the board at 67.7

Humanity's Last Exam (w/ tools) Leaderboard

Pro Mode — raw scores, one benchmark under the lensofficial card harness

The field · 4 measured

54.967.7

4 models measured, most on the official card harness. Claude Opus 5.5 tops the board at 67.7.

4 measured·Lifecycle Updated Nov 4, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 4Bars show 54.9–67.7 · ◆ solid = first-party or better · outlined = arm's-length

01Claude Opus 5.5Anthropic67.7$4.0/M$20.0/M$0.177

02Claude Sonnet 5.5Anthropic64.5$2.0/M$10.0/M$0.093

03Muse Spark 1.1Meta62.1$1.3/M$4.3/M$0.044

04Claude Sonnet 5Anthropic54.9$2.0/M$10.0/M$0.109

◆ solid = independently verified · aggregator attested · vendor attributed — outlined = cross-reference · source-attributed. Dimmed ◆ = confidence inferred. “+N alts” = alternate disclosures in the drawer with why-demoted. Prices per million tokens; $/point = input price ÷ score. Every row opens its model dossier.

Verification: 4 models scored · 0 independently verified · 4 vendor-reported · 0 with source disagreement. How these tiers are assigned