Which model leads MILU?

Q: Which model leads MILU?

Claude Opus 5.5 tops the board at 93.1

MILU Leaderboard — Model Scores

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

The field · 7 measured

87.693.1

7 models measured, most on the official card harness. Claude Opus 5.5 tops the board at 93.1.

7 measured·Lifecycle Updated Nov 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 7Bars show 87.6–93.1 · ◆ solid = first-party or better · outlined = arm's-length

01Claude Opus 5.5+1 altAnthropic93.1$4.0/M$20.0/M$0.129

02Claude Fable 5.1+2 altsAnthropic93$10.0/M$50.0/M$0.323

03Claude Fable 5+1 altAnthropic92.9$10.0/M$50.0/M$0.323

04Claude Opus 5+2 altsAnthropic92.1$5.0/M$25.0/M$0.163

05Claude Sonnet 5.5Anthropic91.6$2.0/M$10.0/M$0.066

06Claude Sonnet 5+2 altsAnthropic89.3$2.0/M$10.0/M$0.067

07Claude Haiku 5.5Anthropic87.6$0.10/M$0.50/M$0.003

◆ 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: 7 models scored · 0 independently verified · 7 vendor-reported · 0 with source disagreement. How these tiers are assigned