Skip to content
VECTOR WIREAI INTELLIGENCE
UTC
Pro Mode — raw scores, one benchmark under the lensthird-party eval harness
The field · 10 measured
40.274.1

10 models measured, most on the third-party eval harness. MiMo V2.5 Pro Base tops the board at 74.1.

10 measured·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 40.2–74.1 · ◆ solid = first-party or better · outlined = arm's-length
01MiMo V2.5 Pro Base+2 altsXiaomi74.1———
02MiMo V2.5 ProXiaomi74.1VENDOR$0.43/M$0.87/M$0.009
03Kimi K2 Base+4 altsMoonshot73.8———
04DeepSeek-V3.1-Base+1 altDeepSeek72.2———
05MiMo V2 Flash Base+1 altXiaomi71.4———
06MiMo V2.5 Base+2 altsXiaomi70.9———
07DeepSeek-V3.2-Exp-Base+1 altDeepSeek69.8———
08Qwen3.5 2BAlibaba57.62VENDOR———
09Qwen3.5 0.8BAlibaba42.33VENDOR———
10ERNIE 4.5Baidu40.2VENDOR———
◆ 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: 10 models scored · 0 independently verified · 3 vendor cross-reference · 7 vendor-reported · 0 with source disagreement. How these tiers are assigned