Which model leads ScreenSpot-V2?

Q: Which model leads ScreenSpot-V2?

Qwen3 VL Thinking (8B) tops the board at 93.6

ScreenSpot-V2 Leaderboard — Model Scores

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

The field · 9 measured

6.993.6

9 models measured, most on the official card harness. Qwen3 VL Thinking (8B) tops the board at 93.6.

9 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 9Bars show 6.9–93.6 · ◆ solid = first-party or better · outlined = arm's-length

01Qwen3 VL Thinking (8B)+1 altAlibaba93.6$0.18/M$2.1/M$0.012

02Kimi VL A3B Instruct+1 altMoonshot92.8———

03Step3 VL 10B+1 altStepFun92.61———

04GLM-4.6V-Flash (9B)+1 altZ.ai92.14$0.30/M$0.90/M$0.007

05Kimi VL A3B ThinkingMoonshot91.43P———

06MiMo VL RL 2508 (7B)+1 altXiaomi90.82———

07InternVL-3.5 (8B)+1 altOpenGVLab84.02———

08GPT-4o+1 altOpenAI18.13P$5.0/M$15.0/M$0.552

09GPT-4o miniOpenAI6.93P$0.15/M$0.60/M$0.054

◆ 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 · 6 vendor cross-reference · 3 vendor-reported · 0 with source disagreement. How these tiers are assigned