Which model leads browsecomp_with_context_manager?

Q: Which model leads browsecomp_with_context_manager?

Gemini 3.1 Pro tops the board at 85.9

browsecomp_with_context_manager Leaderboard

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

The field · 14 measured

57.585.9

14 models measured, most on the official card harness. Gemini 3.1 Pro tops the board at 85.9.

14 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 14Bars show 57.5–85.9 · ◆ solid = first-party or better · outlined = arm's-length

01Gemini 3.1 Pro+1 altGoogle85.9$2.0/M$12.0/M$0.081

02Claude Opus 4.6+1 altAnthropic84$5.0/M$25.0/M$0.179

03GPT-5.4+1 altOpenAI82.7$2.5/M$15.0/M$0.106

04GLM-5.1+1 altZ.ai79.3$1.4/M$4.4/M$0.036

05GLM-5+1 altZ.ai75.9$1.0/M$3.2/M$0.028

06Kimi K2.5+4 altsMoonshot74.9$0.45/M$2.3/M$0.018

07Step 3.5 Flash+2 altsStepFun69$0.10/M$0.30/M$0.003

08DeepSeek-V3.2+5 altsDeepSeek67.6$0.28/M$0.42/M$0.005

09GLM-4.7+3 altsZ.ai67.53P$0.60/M$2.2/M$0.021

10MiniMax M2.1+2 altsMiniMax62$0.30/M$1.2/M$0.012

11Kimi K2 Thinking+4 altsMoonshot60.2$0.60/M$2.5/M$0.026

12Gemini 3 ProGoogle59.23P$2.0/M$12.0/M$0.118

13MiMo V2 Flash+2 altsXiaomi58.3$0.10/M$0.30/M$0.003

14GLM-4.6Z.ai57.53P$0.57/M$2.2/M$0.024

◆ 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