Which model leads VoiceBench?

Gemini 3.1 Pro (high) leads the VoiceBench board of 3 measured models on the Vector Wire tracker at 94.3. Every score is source-attributed with a verification tier.

VoiceBench Leaderboard — Model Scores

Refresh Models —Deals —Regulatory —Sources —

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

The field · 3 measured

9094.3

3 models measured, most on the official card harness. Gemini 3.1 Pro (high) tops the board at 94.3.

3 measured·Lifecycle Updated Sep 1, 2026Basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 3Bars show 90–94.3· ◆ solid = first-party or better · outlined = arm's-length

01Gemini 3.1 Pro (high)Google94.33P$2.0/M$12.0/M$0.074

02Inkling-SmallThinking Machines90.1$0.30/M$1.2/M$0.008

03Inkling+1 altThinking Machines90$0.95/M$4.0/M$0.028

◆ 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.