Which model leads Apex-Shortlist (no tools)?

Q: Which model leads Apex-Shortlist (no tools)?

DeepSeek-V4-Pro tops the board at 85.8

Apex-Shortlist (no tools) Leaderboard — Model Scores

Pro Mode — raw scores, one benchmark under the lensthird-party eval harness

The field · 7 measured

28.985.8

7 models measured, most on the third-party eval harness. DeepSeek-V4-Pro tops the board at 85.8.

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 28.9–85.8 · ◆ solid = first-party or better · outlined = arm's-length

01DeepSeek-V4-ProDeepSeek85.8$0.43/M$0.87/M$0.008

02DeepSeek-V4-FlashDeepSeek82.4$0.44/M$1.3/M$0.011

03Kimi K2.6Moonshot77.4$0.95/M$4.0/M$0.032

04Nemotron 3 Ultra 550B A55BNVIDIA74.9$0.60/M$2.5/M$0.021

05GLM-5.1Z.ai71.1$1.4/M$4.4/M$0.041

06Qwen3.5 397B A17BAlibaba61.4$0.60/M$3.6/M$0.034

07MiniMax M2.7MiniMax28.9$0.21/M$0.84/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: 7 models scored · 0 independently verified · 6 vendor cross-reference · 1 vendor-reported · 0 with source disagreement. How these tiers are assigned