Which model leads MBPP EvalPlus (base)?

Q: Which model leads MBPP EvalPlus (base)?

Llama 3.1 Instruct 405B tops the board at 88.6

MBPP EvalPlus (base) Leaderboard — 4 Models

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

The field · 4 measured

72.888.6

4 models measured, most on the official card harness. Llama 3.1 Instruct 405B tops the board at 88.6.

4 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 4Bars show 72.8–88.6 · ◆ solid = first-party or better · outlined = arm's-length

01Llama 3.1 Instruct 405B+1 altMeta88.6———

02Llama 3.3 70B InstructMeta87.6$0.71/M$0.72/M$0.008

03Llama 3.1 70B InstructMeta86$0.56/M$0.56/M$0.007

04Llama 3.1 8B Instruct+1 altMeta72.8$0.02/M$0.04/M$0.000

◆ 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