Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d263Policy30d65, 14 pendingSources1,013
Pro Mode — raw scores, one benchmark under the lensthird-party eval harness
The field · 15 measured
16.7276.96

15 models measured, most on the third-party eval harness. GPT-5.2 tops the board at 76.96.

15 measured·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 16.72–76.96 · ◆ solid = first-party or better · outlined = arm's-length
01GPT-5.2OpenAI76.96$1.8/M$14.0/M$0.102
02GPT-5.3 CodexOpenAI75.64$1.8/M$14.0/M$0.104
03Claude Opus 4.5Anthropic73.41$5.0/M$25.0/M$0.204
04GPT-5.1 Codex MaxOpenAI71.47$1.3/M$10.0/M$0.079
05Gemini 3 ProGoogle71.34$2.0/M$12.0/M$0.098
06GPT-5OpenAI68.44$1.3/M$10.0/M$0.082
07O3OpenAI64.65$2.0/M$8.0/M$0.077
08Claude Opus 4.1+1 altAnthropic60.61$15.0/M$75.0/M$0.742
09Claude 3.7 SonnetAnthropic54.23$3.0/M$15.0/M$0.166
10O1OpenAI42.57$15.0/M$60.0/M$0.881
11Claude 3.5 SonnetAnthropic40.67$3.0/M$15.0/M$0.221
12GPT-4oOpenAI25$5.0/M$15.0/M$0.400
13Claude 3 OpusAnthropic20.58$15.0/M$75.0/M$2.187
14GPT-4+1 altOpenAI19.71$30.0/M$60.0/M$2.283
15GPT-4 TurboOpenAI16.72$10.0/M$30.0/M$1.196
◆ 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