Skip to content
VECTOR WIREAI INTELLIGENCE
UTC
Pro Mode — raw scores, one benchmark under the lensofficial card harness
The field · 7 measured
32.950.8

7 models measured, most on the official card harness. Ministral 3 3B tops the board at 50.8.

7 measured·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 32.9–50.8 · ◆ solid = first-party or better · outlined = arm's-length
01Ministral 3 3B+1 altMistral50.8$0.10/M$0.10/M$0.002
02Gemma 4 E2B+1 altGoogle47.7———
03Qwen3.5 2B+1 altAlibaba47.4———
04Phi 3.5 Vision Instruct+1 altMicrosoft43.2———
05LFM2.5-VL-1.6B+1 altLiquid AI38———
06Qwen3 VL 2B Instruct+1 altAlibaba37.9———
07North-Micro-Vision-Instruct+1 altCohere32.9———
◆ 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: 7 models scored · 0 independently verified · 7 vendor-reported · 0 with source disagreement. How these tiers are assigned