Which model leads Multimodal understanding (LVBench)?

Q: Which model leads Multimodal understanding (LVBench)?

Gemini 4 Argon tops the board at 91.7

Multimodal understanding (LVBench) Leaderboard

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

The field · 4 measured

79.791.7

4 models measured, most on the official card harness. Gemini 4 Argon tops the board at 91.7.

4 measured·4 new this week·Lifecycle Updated Oct 17, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 4Bars show 79.7–91.7 · ◆ solid = first-party or better · outlined = arm's-length

01Gemini 4 ArgonNEWGoogle91.7$2.0/M$10.0/M$0.065

02GPT-6 AstraNEWOpenAI87.5$10.0/M$50.0/M$0.343

03Claude Opus 5.5NEWAnthropic83.7$4.0/M$20.0/M$0.143

04Claude Fable 5.1NEWAnthropic79.7$10.0/M$50.0/M$0.376

◆ 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 · 3 vendor cross-reference · 1 vendor-reported · 0 with source disagreement. How these tiers are assigned