Which model leads AutomationBench Public?

AutomationBench Public Leaderboard — Model Scores

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

The field · 6 measured

12.830.8

6 models measured, most on the official card harness. Kimi K3 tops the board at 30.8.

6 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 6Bars show 12.8–30.8 · ◆ solid = first-party or better · outlined = arm's-length

01Kimi K3Moonshot30.8$0.58/M$12.3/M$0.209

02Claude Opus 4.8+2 altsAnthropic27.2$5.0/M$25.0/M$0.551

03DeepSeek-V4-Flash-Vision-ExpDeepSeek25.7$0.22/M$0.65/M$0.017

04DeepSeek-V4-Flash+5 altsDeepSeek25.1$0.44/M$1.3/M$0.035

05GLM-5.2+1 altZ.ai12.9$1.4/M$4.4/M$0.225

06DeepSeek-V4-Pro+1 altDeepSeek12.8$0.43/M$0.87/M$0.051

◆ 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: 6 models scored · 0 independently verified · 3 vendor cross-reference · 3 vendor-reported · 1 with source disagreement. How these tiers are assigned