Which model leads Apex Shortlist (Pass@1)?

Q: Which model leads Apex Shortlist (Pass@1)?

Gemini 3.1 Pro tops the board at 89.1

Apex Shortlist (Pass@1) Leaderboard — Model Scores

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

The field · 7 measured

72.489.1

7 models measured, most on the official card harness. Gemini 3.1 Pro tops the board at 89.1.

7 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 7Bars show 72.4–89.1 · ◆ solid = first-party or better · outlined = arm's-length

01Gemini 3.1 Pro+3 altsGoogle89.1$2.0/M$12.0/M$0.079

02Claude Opus 4.6+3 altsAnthropic85.9$5.0/M$25.0/M$0.175

03DeepSeek-V4-FlashDeepSeek85.7$0.44/M$1.3/M$0.010

04DeepSeek-V4-Pro+6 altsDeepSeek85.5$0.43/M$0.87/M$0.008

05GPT-5.4+3 altsOpenAI78.1$2.5/M$15.0/M$0.112

06Kimi K2.6+3 altsMoonshot75.5$0.95/M$4.0/M$0.033

07GLM-5.1+1 altZ.ai72.4$1.4/M$4.4/M$0.040

◆ 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: 7 models scored · 0 independently verified · 5 vendor cross-reference · 2 vendor-reported · 2 with source disagreement. How these tiers are assigned