Which model leads MotionBench?

Q: Which model leads MotionBench?

Seed 2.1 Pro Preview tops the board at 74.9

MotionBench Leaderboard — 9 Models Ranked

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

The field · 9 measured

60.374.9

9 models measured, most on the official card harness. Seed 2.1 Pro Preview tops the board at 74.9.

9 measured·Lifecycle Updated Oct 9, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 9Bars show 60.3–74.9 · ◆ solid = first-party or better · outlined = arm's-length

01Seed 2.1 Pro Preview+1 altByteDance74.9———

02Seed2.1ByteDance74.8———

03Seed 1.8ByteDance70.6$0.25/M$2.0/M$0.016

04Gemini 3.5 FlashGoogle70.6$1.5/M$9.0/M$0.074

05Kimi K2.5+1 altMoonshot70.4$0.45/M$2.3/M$0.019

06Gemini 3 ProGoogle70.33P$2.0/M$12.0/M$0.100

07Gemini 3.1 ProGoogle69.9$2.0/M$12.0/M$0.100

08GPT-5.2OpenAI64.83P$1.8/M$14.0/M$0.122

09Claude Opus 4.5Anthropic60.33P$5.0/M$25.0/M$0.249

◆ 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: 9 models scored · 0 independently verified · 5 vendor cross-reference · 4 vendor-reported · 0 with source disagreement. How these tiers are assigned