Which model leads BrowseComp (context management)?

Q: Which model leads BrowseComp (context management)?

GPT-5.6 Luna tops the board at 84

BrowseComp (context management) Leaderboard — Model Scores

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

The field · 14 measured

26.184

14 models measured, most on the third-party eval harness. GPT-5.6 Luna tops the board at 84.

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 26.1–84 · ◆ solid = first-party or better · outlined = arm's-length

01GPT-5.6 Luna+1 altOpenAI84VENDOR$0.20/M$1.2/M$0.008

02Qwen3.5 397B A17BAlibaba78.6VENDOR$0.60/M$3.6/M$0.027

03Inkling-SmallThinking Machines77.4VENDOR$0.30/M$1.2/M$0.010

04InklingThinking Machines77.1$0.95/M$4.0/M$0.032

05MiniMax M2.7MiniMax76.3VENDOR$0.21/M$0.84/M$0.007

06DeepSeek-V4-FlashDeepSeek73.2VENDOR$0.44/M$1.3/M$0.012

07GPT-5.2OpenAI70$1.8/M$14.0/M$0.113

08DeepSeek-V3.2DeepSeek67.6$0.28/M$0.42/M$0.005

09Nemotron 3 Ultra 550B A55BNVIDIA63VENDOR$0.60/M$2.5/M$0.025

10MiniMax M2.1MiniMax62$0.30/M$1.2/M$0.012

11Gemini 3 ProGoogle59.2$2.0/M$12.0/M$0.118

12Claude Opus 4.5Anthropic57.8$5.0/M$25.0/M$0.260

13MiniMax M2MiniMax56.9$0.30/M$1.2/M$0.013

14Claude Sonnet 4.5Anthropic26.1$3.0/M$15.0/M$0.345

◆ 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 · 10 vendor cross-reference · 4 vendor-reported · 0 with source disagreement. How these tiers are assigned