Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d261Policy30d65, 14 pendingSources1,013
Pro Mode — raw scores, one benchmark under the lensthird-party eval harness
The field · 15 measured
98.48100

15 models measured, most on the third-party eval harness. GPT-5.1 Codex Max tops the board at 100.

15 measured·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 98.48–100 · ◆ solid = first-party or better · outlined = arm's-length
01GPT-5.1 Codex MaxOpenAI100$1.3/M$10.0/M$0.056
02Claude Opus 4.1+1 altAnthropic100$15.0/M$75.0/M$0.450
03O1OpenAI100$15.0/M$60.0/M$0.375
04Claude Opus 4Anthropic99.75$15.0/M$75.0/M$0.451
05GPT-5.2OpenAI99.62$1.8/M$14.0/M$0.079
06GPT-5.3 CodexOpenAI99.49$1.8/M$14.0/M$0.079
07Gemini 3 ProGoogle99.49$2.0/M$12.0/M$0.070
08GPT-4 TurboOpenAI99.49$10.0/M$30.0/M$0.201
09Claude Opus 4.5Anthropic99.49$5.0/M$25.0/M$0.151
10GPT-4oOpenAI99.24$5.0/M$15.0/M$0.101
11Claude 3.7 SonnetAnthropic98.74$3.0/M$15.0/M$0.091
12Claude 3.5 SonnetAnthropic98.74$3.0/M$15.0/M$0.091
13Claude 3 OpusAnthropic98.48$15.0/M$75.0/M$0.457
14Claude Opus 4.6Anthropic98.48$5.0/M$25.0/M$0.152
15GPT-4+1 altOpenAI98.48$30.0/M$60.0/M$0.457
◆ 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: 15 models scored · 15 independently verified · 0 with source disagreement. How these tiers are assigned