Which model leads CharadesSTA?

Qwen3 VL 235B A22B Instruct leads the CharadesSTA board of 11 measured models on the Vector Wire tracker at 64.8. Every score is source-attributed with a verification tier.

CharadesSTA Leaderboard — Model Scores

Refresh Models —Deals —Regulatory —Sources —

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

The field · 11 measured

54.264.8

11 models measured, most on the official card harness. Qwen3 VL 235B A22B Instruct tops the board at 64.8.

11 measured·11 new this week·Lifecycle Updated Aug 27, 2026Basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 11Bars show 54.2–64.8· ◆ solid = first-party or better · outlined = arm's-length

01Qwen3 VL 235B A22B InstructNEWAlibaba64.8$0.40/M$1.6/M$0.015

02Qwen3 VL 235B A22B ThinkingNEWAlibaba63.5$0.40/M$4.0/M$0.035

03Qwen3 VL 30B A3B InstructNEWAlibaba63.5$0.20/M$0.80/M$0.008

04Qwen3 VL 32B ThinkingNEWAlibaba62.8$0.16/M$0.64/M$0.006

05Qwen3 VL 30B A3B ThinkingNEWAlibaba62.7$0.20/M$2.4/M$0.021

06Qwen3 VL 32B InstructNEWAlibaba61.2$0.16/M$0.64/M$0.007

07Qwen3 VL 8B ThinkingNEWAlibaba59.9$0.18/M$2.1/M$0.019

08Qwen3 VL 4B ThinkingNEWAlibaba59———

09Qwen3 VL 8B InstructNEWAlibaba56$0.18/M$0.70/M$0.008

10Qwen3 VL 4B InstructNEWAlibaba55.5———

11Qwen2.5 VL 32B InstructNEW+1 altAlibaba54.2———

◆ 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.