Which model leads QwenWebBench?

Q: Which model leads QwenWebBench?

Claude Opus 4.5 tops the board at 1,536

QwenWebBench Leaderboard — Model Scores

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

The field · 8 measured

9781,536

8 models measured, most on the third-party eval harness. Claude Opus 4.5 tops the board at 1,536.

8 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 8Bars show 978–1,536 · ◆ solid = first-party or better · outlined = arm's-length

01Claude Opus 4.5Anthropic1,536$5.0/M$25.0/M$0.010

02Qwen3.6 27BAlibaba1,487$0.60/M$3.6/M$0.001

03Qwen3.6 35B A3B+1 altAlibaba1,397$0.38/M$2.3/M$0.001

04Gemma 4 31B+1 altGoogle1,197$0.17/M$0.40/M$0.000

05Qwen3.5 397B A17BAlibaba1,186$0.60/M$3.6/M$0.002

06Gemma 4 26B A4BGoogle1,178$0.07/M$0.34/M$0.000

07Qwen3.5 27B+1 altAlibaba1,068$0.30/M$2.4/M$0.001

08Qwen3.5 35B A3BAlibaba978$0.25/M$2.0/M$0.001

◆ 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: 8 models scored · 0 independently verified · 3 vendor cross-reference · 5 vendor-reported · 0 with source disagreement. How these tiers are assigned