Skip to content
VECTOR WIREAI INTELLIGENCE
UTC
Pro Mode — raw scores, one benchmark under the lensofficial card harness
The field · 15 measured
33.0968.2

15 models measured, most on the official card harness. Gemma 4 E4B tops the board at 68.2.

15 measured·3 new this week·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 33.09–68.2 · ◆ solid = first-party or better · outlined = arm's-length
01Gemma 4 E4BGoogle68.2$0.02/M$0.10/M$0.001
02Gemma 4 E2B+1 altGoogle65.6———
03Qwen3.5 4BAlibaba63.1$0.03/M$0.15/M$0.001
04LFM2.5-VL-3B+2 altsLiquid AI60.6———
05Qwen3.5 2BAlibaba55.4———
06InternVL3_5-4BOpenGVLab54.5———
07LFM2.5-VL-1.6BLiquid AI52.293P———
08LFM2-VL-3B+2 altsLiquid AI51.4———
09InternVL3_5-2B+1 altOpenGVLab47.1———
10LFM2-VL-1.6BNEW+1 altLiquid AI46.353P———
11LFM2.5-VL-450M-ExtractLiquid AI453P———
12Qwen2.5 VL 3BAlibaba38.623P———
13InternVL3-2BNEW+1 altOpenGVLab38.493P———
14InternVL3.5-1BOpenGVLab36.173P———
15LFM2-VL-450MNEW+1 altLiquid AI33.093P———
◆ 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: 15 models scored · 0 independently verified · 4 vendor cross-reference · 11 vendor-reported · 0 with source disagreement. How these tiers are assigned