Which model leads DROP (3-shot F1)?

Q: Which model leads DROP (3-shot F1)?

DeepSeek-R1 tops the board at 92.2

DROP (3-shot F1) Leaderboard — 15 Models

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

The field · 15 measured

71.292.2

15 models measured, most on the official card harness. DeepSeek-R1 tops the board at 92.2.

15 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 15Bars show 71.2–92.2 · ◆ solid = first-party or better · outlined = arm's-length

01DeepSeek-R1+5 altsDeepSeek92.2$2.0/M$4.0/M$0.033

02DeepSeek-V3+5 altsDeepSeek91.6$0.24/M$0.90/M$0.006

03O1+4 altsOpenAI90.2$15.0/M$60.0/M$0.416

04DeepSeek-R1-ZeroDeepSeek89.1———

05Llama 3.1 Instruct 405BMeta88.7———

06Claude 3.5 Sonnet+10 altsAnthropic88.3$3.0/M$15.0/M$0.102

07DeepSeek-V2.5DeepSeek87.8———

08DeepSeek-R1-Distill-Qwen-14B+4 altsDeepSeek85.5$0.20/M$0.20/M$0.002

09O1 Mini+9 altsOpenAI83.9———

10GPT-4o+10 altsOpenAI83.7$5.0/M$15.0/M$0.119

11DeepSeek-V2DeepSeek83———

12MiMo 7B RL+4 altsXiaomi78.7———

13DeepSeek-R1-Distill-Qwen-7B+4 altsDeepSeek77$0.15/M$0.15/M$0.002

14Qwen2.5 Instruct 72BAlibaba76.7$0.47/M$0.49/M$0.006

15QwQ 32B Preview+4 altsAlibaba71.2$0.66/M$1.0/M$0.012

◆ 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: 15 models scored · 0 independently verified · 9 vendor cross-reference · 6 vendor-reported · 0 with source disagreement. How these tiers are assigned