VECTOR WIREAI INTELLIGENCE
UTC
Refresh Models Deals Regulatory Sources
Pro Mode — raw scores, one benchmark under the lensofficial card harness
The field · 7 measured
682

7 models measured, most on the official card harness. InternVL 3.5 4B tops the board at 82.

7 measured·6 new this week·Lifecycle Updated Sep 12, 2026Basis
#Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 682· ◆ solid = first-party or better · outlined = arm's-length
01InternVL 3.5 4BNEWOpenGVLab82
02InternVL 3.5 2BNEWOpenGVLab79.9
03LFM2.5-VL-3BLiquid AI78.7
04Qwen3.5-2BNEWAlibaba63.8
05gemma-4-E4B-itNEWGoogle45.8$0.02/M$0.10/M$0.001
06gemma-4-E2B-itNEWGoogle28.1
07LFM2-VL-3BNEWLiquid AI6
◆ 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.