Which model leads DeepPlanning?

Q: Which model leads DeepPlanning?

Qwen3.7 Plus Preview tops the board at 62.3

DeepPlanning Leaderboard — Model Scores

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

The field · 12 measured

16.262.3

12 models measured, most on the official card harness. Qwen3.7 Plus Preview tops the board at 62.3.

12 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 12Bars show 16.2–62.3 · ◆ solid = first-party or better · outlined = arm's-length

01Qwen3.7 Plus PreviewAlibaba62.3$0.40/M$1.6/M$0.016

02Qwen3.6 PlusAlibaba41.5$0.50/M$3.0/M$0.042

03Qwen3.5 397B A17BAlibaba34.3$0.60/M$3.6/M$0.061

04Qwen3 Max (Reasoning)Alibaba28.7$1.2/M$6.0/M$0.125

05Qwen3.6 35B A3B+1 altAlibaba25.9$0.38/M$2.3/M$0.051

06Qwen3.5 122B A10BAlibaba24.1$0.40/M$3.2/M$0.075

07Gemma 4 31BGoogle243P$0.17/M$0.40/M$0.012

08Qwen3.5 35B A3B+1 altAlibaba22.8$0.25/M$2.0/M$0.049

09Qwen3.5 27B+1 altAlibaba22.6$0.30/M$2.4/M$0.060

10Qwen3.5 9BAlibaba18$0.14/M$0.20/M$0.009

11Qwen3.5 4BAlibaba17.6$0.03/M$0.15/M$0.005

12Gemma 4 26B A4BGoogle16.23P$0.07/M$0.34/M$0.013

◆ 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: 12 models scored · 0 independently verified · 2 vendor cross-reference · 10 vendor-reported · 0 with source disagreement. How these tiers are assigned