Which model leads OpenAI-MRCR (1M)?

Opus-4.6 Max leads the OpenAI-MRCR (1M) board of 7 measured models on the Vector Wire tracker at 92.9. Every score is source-attributed with a verification tier.

OpenAI-MRCR (1M) Leaderboard — Model Scores

Refresh Models —Deals —Regulatory —Sources —

Pro Mode — raw scores, one benchmark under the lensofficial card harness

The field · 7 measured

56.292.9

7 models measured, most on the official card harness. Opus-4.6 Max tops the board at 92.9.

7 measured·Lifecycle Updated Sep 7, 2026Basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 7Bars show 56.2–92.9· ◆ solid = first-party or better · outlined = arm's-length

01Opus-4.6 Max+3 altsAnthropic92.9$5.0/M$25.0/M$0.161

02V4-Pro High+6 altsDeepSeek83.3$1.3/M$4.0/M$0.032

03V4-Flash Non-ThinkDeepSeek78.7$0.44/M$1.3/M$0.011

04Gemini-3.1-Pro High+3 altsGoogle76.3$2.0/M$12.0/M$0.092

05Gemini 2.5 Pro (06-05)+1 altGoogle58.83P$1.3/M$10.0/M$0.096

06MiniMax-M1-40K+1 altMiniMax58.63P———

07MiniMax-M1-80K+1 altMiniMax56.23P$0.55/M$2.2/M$0.024

◆ 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.