Skip to content
VECTOR WIREAI INTELLIGENCE
UTC
Pro Mode — raw scores, one benchmark under the lensthird-party eval harness
The field · 11 measured
35.596.7

11 models measured, most on the third-party eval harness. Nemotron 3 Super 120B A12B tops the board at 96.7.

11 measured·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 35.5–96.7 · ◆ solid = first-party or better · outlined = arm's-length
01Nemotron 3 Super 120B A12B+1 altNVIDIA96.7$0.30/M$0.90/M$0.006
03MiniMax Text 01MiniMax94.5———
04Gemini 1.5 ProGoogle91.6———
05Nemotron 3 Ultra 550B A55B BaseNVIDIA86.22———
06Gemma 4 26B A4BGoogle85.73$0.07/M$0.34/M$0.002
07Qwen3.5 35B A3BAlibaba82.36$0.25/M$2.0/M$0.014
08Gemini 2.0 Flash ExpGoogle79.7———
09Nemotron 3.5 LightningNVIDIA76.88$0.06/M$0.20/M$0.002
10NVIDIA Nemotron 3 Nano 30B A3BNVIDIA71.71$0.05/M$0.20/M$0.002
11Mistral Large 3 675B Base 2512Mistral35.5———
◆ 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: 11 models scored · 0 independently verified · 5 vendor cross-reference · 6 vendor-reported · 1 with source disagreement. How these tiers are assigned