Skip to content
VECTOR WIREAI INTELLIGENCE
UTC
Pro Mode — raw scores, one benchmark under the lensthird-party eval harness
The field · 9 measured
38.352

9 models measured, most on the third-party eval harness. Kimi K2.6 tops the board at 52.

9 measured·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 38.3–52 · ◆ solid = first-party or better · outlined = arm's-length
01Kimi K2.6Moonshot52$0.95/M$4.0/M$0.048
02DeepSeek-V4-ProDeepSeek50.5$0.43/M$0.87/M$0.013
03DeepSeek-V4-FlashDeepSeek48.2$0.44/M$1.3/M$0.018
04Qwen3.5 397B A17BAlibaba48$0.60/M$3.6/M$0.044
05GLM-5.1Z.ai47.7$1.4/M$4.4/M$0.061
06Nemotron 3 Ultra 550B A55B+1 altNVIDIA43.5VENDOR$0.60/M$2.5/M$0.036
07Nemotron 3 Super 120B A12BNVIDIA42.3$0.30/M$0.90/M$0.014
09MiniMax M2.7MiniMax38.3$0.21/M$0.84/M$0.014
◆ 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: 9 models scored · 0 independently verified · 6 vendor cross-reference · 3 vendor-reported · 0 with source disagreement. How these tiers are assigned