Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d67, 15 pendingSources1,014
Pro Mode — raw scores, one benchmark under the lensofficial card harness
The field · 26 measured
1470

26 models measured, most on the official card harness. Claude Sonnet 4.5 tops the board at 70.

26 measured·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 14–70 · ◆ solid = first-party or better · outlined = arm's-length
01Claude Sonnet 4.5Anthropic70$3.0/M$15.0/M$0.129
02MiniMax M1 80K+2 altsMiniMax62$0.55/M$2.2/M$0.022
03GLM-4.5-AirZ.ai60.8$0.17/M$0.98/M$0.009
04GLM-4.5Z.ai60.4$0.60/M$2.2/M$0.023
05MiniMax M1 40K+2 altsMiniMax60———
06Claude Sonnet 4Anthropic60$3.0/M$15.0/M$0.150
07Qwen3 Coder 480B A35B InstructAlibaba60$1.5/M$7.5/M$0.075
08Claude Opus 4+2 altsAnthropic59.6$15.0/M$75.0/M$0.755
09Claude 3.7 SonnetAnthropic58.4$3.0/M$15.0/M$0.154
10Claude Opus 4.1Anthropic56$15.0/M$75.0/M$0.804
11O3+1 altOpenAI523P$2.0/M$8.0/M$0.096
12Gemini 2.5 Pro+1 altGoogle503P$1.3/M$10.0/M$0.113
13GPT-4.5 PreviewOpenAI50———
14O1OpenAI50$15.0/M$60.0/M$0.750
15GPT-4.1OpenAI49.4$2.0/M$8.0/M$0.101
16O4 MiniOpenAI49.2$1.1/M$4.4/M$0.056
17Qwen3 Next 80B A3BAlibaba49$0.15/M$1.2/M$0.014
18Claude 3.5 SonnetAnthropic46$3.0/M$15.0/M$0.196
19Seed Oss 36B InstructByteDance463P$0.21/M$0.57/M$0.008
20Qwen3 Next 80B A3B InstructAlibaba44$0.15/M$1.2/M$0.015
21GPT-4oOpenAI42.8$5.0/M$15.0/M$0.234
22GPT-4.1 miniOpenAI36$0.40/M$1.6/M$0.028
23Qwen3 235B A22B+1 altAlibaba34.73P$0.70/M$2.8/M$0.050
24O3 MiniOpenAI32.4$1.1/M$4.4/M$0.085
25Claude 3.5 HaikuAnthropic22.8———
26GPT-4.1 nanoOpenAI14$0.10/M$0.40/M$0.018
◆ 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: 26 models scored · 0 independently verified · 3 vendor cross-reference · 23 vendor-reported · 0 with source disagreement. How these tiers are assigned