Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d261Policy30d65, 14 pendingSources1,013
Pro Mode — raw scores, one benchmark under the lensofficial card harness
The field · 16 measured
7.274.4

16 models measured, most on the official card harness. Gemma 4 31B tops the board at 74.4.

16 measured·5 new this week·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 7.2–74.4 · ◆ solid = first-party or better · outlined = arm's-length
01Gemma 4 31BNEW+27 altsGoogle74.4$0.17/M$0.40/M$0.004
02Gemma 4 26B A4BNEW+31 altsGoogle64.8$0.07/M$0.34/M$0.003
03Gemma 4 12B+23 altsGoogle53$0.10/M$0.30/M$0.004
04Gemma 4 E4BNEW+31 altsGoogle33.1$0.02/M$0.10/M$0.002
05DeepSeek-V4-Pro-BaseDeepSeek29.8———
06SynLogic Mix 3 32BMiniMax28.63P———
07SynLogic 32BMiniMax25.53P———
08DeepSeek-V4-Flash-BaseDeepSeek25.4———
09Gemma 4 E2BNEW+36 altsGoogle21.9———
10Gemma 3 27BNEW+28 altsGoogle19.3$0.08/M$0.16/M$0.006
11DeepSeek-R1-Distill-Qwen-32B+1 altDeepSeek19.23P$0.29/M$0.29/M$0.015
12Qwen2.5 Instruct 32BAlibaba17.53P———
13Gemma 3 12BGoogle16.3$0.05/M$0.15/M$0.006
14Gemma 3 4BGoogle11$0.05/M$0.10/M$0.007
15SynLogic 7BMiniMax83P———
16Gemma 3 1B InstructGoogle7.2———
◆ 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: 16 models scored · 0 independently verified · 2 vendor cross-reference · 14 vendor-reported · 0 with source disagreement. How these tiers are assigned