Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models739Deals30d256Policy30d64, 14 pendingSources1,010
Pro Mode — raw scores, one benchmark under the lensthird-party eval harness
The field · 18 measured
13.5275.8

18 models measured, most on the third-party eval harness. MiniMax M2.5 tops the board at 75.8.

18 measured·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 13.52–75.8 · ◆ solid = first-party or better · outlined = arm's-length
01MiniMax M2.5MiniMax75.8$0.27/M$1.1/M$0.009
02Gemini 3 Flash PreviewGoogle75.8$0.50/M$3.0/M$0.023
03Claude Opus 4.5+3 altsAnthropic74.4$5.0/M$25.0/M$0.202
04GLM-5Z.ai72.8$1.0/M$3.2/M$0.029
05Claude Sonnet 4.5+3 altsAnthropic71.4$3.0/M$15.0/M$0.126
06Kimi K2.5Moonshot70.8$0.45/M$2.3/M$0.019
07GPT-5.2+2 altsOpenAI69$1.8/M$14.0/M$0.114
08GPT-5.1+3 altsOpenAI66$1.3/M$10.0/M$0.085
09GPT-5.1 Codex+1 altOpenAI66$1.3/M$10.0/M$0.085
10GPT-5+1 altOpenAI65$1.3/M$10.0/M$0.087
11Kimi K2 ThinkingMoonshot63.4$0.60/M$2.5/M$0.024
12DeepSeek-V3.2DeepSeek60$0.26/M$0.38/M$0.005
13GPT-5 miniOpenAI59.8$0.25/M$2.0/M$0.019
14Qwen3 Coder 480B A35B InstructAlibaba55.4$1.5/M$7.5/M$0.081
15Claude 3.7 SonnetAnthropic52.8$3.0/M$15.0/M$0.170
16GPT-5 nanoOpenAI34.8$0.05/M$0.40/M$0.006
17GPT-4.1 miniOpenAI23.94$0.40/M$1.6/M$0.042
18Gemini 2.0 Flash (Reasoning)Google13.52———
◆ 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: 18 models scored · 18 independently verified · 0 with source disagreement. How these tiers are assigned