Skip to content
VECTOR WIREAI INTELLIGENCE
UTC
Pro Mode — raw scores, one benchmark under the lensscaffolded harness
The field · 3 measured
4.3358.33

3 models measured, most on the scaffolded harness. Claude Sonnet 4 tops the board at 58.33.

3 measured·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 4.33–58.33 · ◆ solid = first-party or better · outlined = arm's-length
01Claude Sonnet 4Anthropic58.33$3.0/M$15.0/M$0.154
02Qwen3 Coder 30B A3B InstructAlibaba45$0.45/M$2.3/M$0.030
03Claude 3 OpusAnthropic4.33$15.0/M$75.0/M$10.393
◆ 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: 3 models scored · 3 independently verified · 0 with source disagreement. How these tiers are assigned