Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models739Deals30d267Policy30d64, 15 pendingSources1,010
Pro Mode — raw scores, one benchmark under the lensofficial card harness
The field · 24 measured
12.591.2

24 models measured, most on the official card harness. Claude Opus 5.5 tops the board at 91.2.

24 measured·1 new this week·Lifecycle Updated Oct 7, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 12.5–91.2 · ◆ solid = first-party or better · outlined = arm's-length
01Claude Opus 5.5+3 altsAnthropic91.2$4.0/M$20.0/M$0.132
02Claude Mythos 5.1Anthropic87.6$10.0/M$50.0/M$0.342
03Claude Fable 5.1+1 altAnthropic87.6$10.0/M$50.0/M$0.342
04Claude Fable 5+3 altsAnthropic86.3$10.0/M$50.0/M$0.348
05Claude Opus 5+3 altsAnthropic85.4$5.0/M$25.0/M$0.176
06Haiku 5.5NEWAnthropic82———
07Sonnet 5.5+2 altsAnthropic79.7$2.0/M$10.0/M$0.075
08Kimi K3+1 altMoonshot77.8$0.62/M$15.0/M$0.100
09Claude Sonnet 5Anthropic77.3$2.0/M$10.0/M$0.078
10Claude Opus 4.8+3 altsAnthropic71.9$5.0/M$25.0/M$0.209
11GPT-5.5+3 altsOpenAI70.8$5.0/M$30.0/M$0.247
12GLM-5.2+4 altsZ.ai63.7$1.4/M$4.4/M$0.046
13Kimi K2.7 Code+1 altMoonshot53.6$1.9/M$8.1/M$0.093
14GLM-5.1+1 altZ.ai50.9$1.4/M$4.4/M$0.057
15Seed 2.1 Pro PreviewByteDance50.3———
16DeepSeek-V4-Pro+1 altDeepSeek47.8$0.43/M$0.87/M$0.014
17Gemini 3.1 Pro+1 altGoogle39.5$2.0/M$12.0/M$0.177
18MiMo V2.6 Pro+2 altsXiaomi26.5$0.43/M$0.87/M$0.025
19MiMo V2.6 Flash RL+2 altsXiaomi26$0.14/M$0.28/M$0.008
20GPT-5.6 Sol+2 altsOpenAI253P$4.0/M$20.0/M$0.480
21DeepSeek-V4.1-FlashDeepSeek20.3$0.05/M$1.2/M$0.031
22GLM-5.3Z.ai19$1.4/M$4.4/M$0.153
23Hy4Tencent17.5$0.83/M$2.5/M$0.095
24MiMo V2.5 Pro+1 altXiaomi12.53P$0.43/M$0.87/M$0.052
◆ 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: 24 models scored · 0 independently verified · 5 vendor cross-reference · 19 vendor-reported · 0 with source disagreement. How these tiers are assigned