Which model leads AgentWorldBench - Overall?

Q: Which model leads AgentWorldBench - Overall?

Qwen AgentWorld 397B A17B tops the board at 58.71

AgentWorldBench - Overall Leaderboard — Model Scores

Pro Mode — raw scores, one benchmark under the lensthird-party eval harness

The field · 14 measured

46.1258.71

14 models measured, most on the third-party eval harness. Qwen AgentWorld 397B A17B tops the board at 58.71.

14 measured·Lifecycle Updated Oct 7, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 14Bars show 46.12–58.71 · ◆ solid = first-party or better · outlined = arm's-length

01Qwen AgentWorld 397B A17BAlibaba58.71———

02GPT-5.4OpenAI58.25$2.5/M$15.0/M$0.150

03Claude Opus 4.6Anthropic57.8$5.0/M$25.0/M$0.260

04Claude Opus 4.8Anthropic56.59$5.0/M$25.0/M$0.265

05Qwen AgentWorld 35B A3BAlibaba56.39———

06Claude Sonnet 4.6Anthropic56.04$3.0/M$15.0/M$0.161

07Qwen3.5 397B A17BAlibaba54.74$0.60/M$3.6/M$0.038

08Gemini 3.1 ProGoogle54.57$2.0/M$12.0/M$0.128

09Kimi K2.6Moonshot53.42$0.95/M$4.0/M$0.046

10DeepSeek-V4-ProDeepSeek52.97$0.43/M$0.87/M$0.012

11GLM-5.1Z.ai51.31$1.4/M$4.4/M$0.056

12Qwen3.6 PlusAlibaba50.81$0.50/M$3.0/M$0.034

13Qwen3.5 35B A3BAlibaba47.73$0.25/M$2.0/M$0.024

14MiniMax M2.7MiniMax46.12$0.21/M$0.84/M$0.011

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