Which model leads GlobalMMLU?

Q: Which model leads GlobalMMLU?

Claude Opus 5.5 tops the board at 94.3

GlobalMMLU Leaderboard — Model Scores

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

The field · 10 measured

76.694.3

10 models measured, most on the official card harness. Claude Opus 5.5 tops the board at 94.3.

10 measured·1 new this week·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 10Bars show 76.6–94.3 · ◆ solid = first-party or better · outlined = arm's-length

01Claude Opus 5.5Anthropic94.3$4.0/M$20.0/M$0.127

02Sonnet 5.5Anthropic92.1$2.0/M$10.0/M$0.065

03Haiku 5.5NEWAnthropic87.8$0.10/M$0.50/M$0.003

04MiMo V2.5 ProXiaomi83.6$0.43/M$0.87/M$0.008

05MiMo V2.5 Pro Base+2 altsXiaomi83.6———

06DeepSeek-V3.2-Exp-BaseDeepSeek823P———

07DeepSeek-V3.1-BaseDeepSeek81.93P———

08Kimi K2 Base+3 altsMoonshot80.7———

09MiMo V2.5 Base+2 altsXiaomi77.4———

10MiMo V2 Flash BaseXiaomi76.63P———

◆ 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: 10 models scored · 0 independently verified · 3 vendor cross-reference · 7 vendor-reported · 0 with source disagreement. How these tiers are assigned