Which model leads QwenClawBench?

Q: Which model leads QwenClawBench?

Qwen3.7 Plus Preview tops the board at 61.8

QwenClawBench Leaderboard — 9 Models Ranked

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

The field · 9 measured

38.761.8

9 models measured, most on the third-party eval harness. Qwen3.7 Plus Preview tops the board at 61.8.

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 38.7–61.8 · ◆ solid = first-party or better · outlined = arm's-length

01Qwen3.7 Plus PreviewAlibaba61.8VENDOR$0.40/M$1.6/M$0.016

02Qwen3.6 27BAlibaba53.4$0.60/M$3.6/M$0.039

03Qwen3.6 35B A3B+1 altAlibaba52.6$0.38/M$2.3/M$0.025

04Claude Opus 4.5Anthropic52.3$5.0/M$25.0/M$0.287

05Qwen3.5 27B+1 altAlibaba52.2$0.30/M$2.4/M$0.026

06Qwen3.5 397B A17BAlibaba51.8$0.60/M$3.6/M$0.041

07Qwen3.5 35B A3BAlibaba47.7$0.25/M$2.0/M$0.024

08Gemma 4 31B+1 altGoogle41.7$0.17/M$0.40/M$0.007

09Gemma 4 26B A4BGoogle38.7$0.07/M$0.34/M$0.005

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