Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d268Policy30d67, 15 pendingSources1,014
Pro Mode — raw scores, one benchmark under the lensthird-party eval harness
The field · 14 measured
1752.7

14 models measured, most on the third-party eval harness. MiniMax M2.7 tops the board at 52.7.

14 measured·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 17–52.7 · ◆ solid = first-party or better · outlined = arm's-length
01MiniMax M2.7MiniMax52.7VENDOR$0.21/M$0.84/M$0.010
02MiniMax M2.5+1 altMiniMax51.3VENDOR$0.27/M$1.1/M$0.013
03Claude Opus 4.5Anthropic50$5.0/M$25.0/M$0.300
04MiniMax M2.1+1 altMiniMax49.4VENDOR$0.30/M$1.2/M$0.015
05Claude Sonnet 4.5+1 altAnthropic44.3$3.0/M$15.0/M$0.203
06Gemini 3 ProGoogle42.7$2.0/M$12.0/M$0.164
07Seed 1.8ByteDance42VENDOR$0.25/M$2.0/M$0.027
08MiniMax M2+2 altsMiniMax36.2VENDOR$0.30/M$1.2/M$0.021
09Claude Sonnet 4Anthropic35.7$3.0/M$15.0/M$0.252
10Kimi K2 InstructMoonshot33.5$0.57/M$2.3/M$0.043
11DeepSeek-V3.2+1 altDeepSeek30.6$0.28/M$0.42/M$0.011
12GLM-4.6Z.ai30$0.57/M$2.2/M$0.046
13Qwen3 Coder 480B A35B InstructAlibaba25.8VENDOR$1.5/M$7.5/M$0.174
14Seed Oss 36B InstructByteDance17$0.21/M$0.57/M$0.023
◆ 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: 14 models scored · 0 independently verified · 7 vendor cross-reference · 7 vendor-reported · 0 with source disagreement. How these tiers are assigned