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 · 17 measured
61.05699.068

17 models measured, most on the third-party eval harness. Claude Opus 4 tops the board at 99.068.

17 measured·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 61.056–99.068 · ◆ solid = first-party or better · outlined = arm's-length
01Claude Opus 4Anthropic99.068$15.0/M$75.0/M$0.454
02Qwen3 235B A22BAlibaba99.068$0.70/M$2.8/M$0.018
03O3 Mini+2 altsOpenAI99.068$1.1/M$4.4/M$0.028
04Gemini 2.5 Flash+1 altGoogle99.068$0.30/M$2.5/M$0.014
05O3OpenAI99.068VENDOR$2.0/M$8.0/M$0.050
06EXAONE 4.0 32BLG AI98.835VENDOR———
07O4 Mini+2 altsOpenAI98.758VENDOR$1.1/M$4.4/M$0.028
08Gemini 2.5 Pro+1 altGoogle98.758$1.3/M$10.0/M$0.057
09Claude Sonnet 4Anthropic98.758$3.0/M$15.0/M$0.091
10OpenReasoning-Nemotron-32BNVIDIA98.603———
11Grok 3 Mini ReasoningSpaceXAI98.137$0.30/M$0.50/M$0.004
12OpenCodeReasoning-Nemotron-1.1-32BNVIDIA98.012VENDOR———
13DeepSeek-V3DeepSeek83.292$0.24/M$0.90/M$0.007
14GPT-4oOpenAI82.516$5.0/M$15.0/M$0.121
15GPT-4o miniOpenAI81.708$0.15/M$0.60/M$0.005
16GPT-4 TurboOpenAI81.398$10.0/M$30.0/M$0.246
17Claude 3 HaikuAnthropic61.056$0.25/M$1.3/M$0.012
◆ 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: 17 models scored · 17 independently verified · 0 with source disagreement. How these tiers are assigned