Which model leads GDPval-AA v2 Elo?

Q: Which model leads GDPval-AA v2 Elo?

Claude Fable 5.1 tops the board at 1,835

GDPval-AA v2 Elo Leaderboard — Model Scores

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

The field · 19 measured

9651,835

19 models measured, most on the official card harness. Claude Fable 5.1 tops the board at 1,835.

19 measured·Lifecycle Updated Oct 16, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 19Bars show 965–1,835 · ◆ solid = first-party or better · outlined = arm's-length

01Claude Fable 5.1Anthropic1,835$10.0/M$50.0/M$0.016

02Claude Opus 5+1 altAnthropic1,824$5.0/M$25.0/M$0.008

03Claude Fable 5+1 altAnthropic1,723$10.0/M$50.0/M$0.017

04GPT-5.6 Sol+1 altOpenAI1,710$4.0/M$20.0/M$0.007

05Kimi K3Moonshot1,6863P$0.30/M$12.3/M$0.004

06Muse Spark 1.2Meta1,628$1.3/M$4.3/M$0.002

07Claude Opus 4.8Anthropic1,5933P$5.0/M$25.0/M$0.009

08GPT-5.6 LunaOpenAI1,584$0.20/M$1.2/M$0.000

09Claude Sonnet 5Anthropic1,584$2.0/M$10.0/M$0.004

10Gemini 3.8 FlashGoogle1,545$0.75/M$3.8/M$0.001

11Grok4.5SpaceXAI1,535$2.0/M$6.0/M$0.003

12GPT-5.6 TerraOpenAI1,528$2.0/M$12.0/M$0.005

13GLM-5.2Z.ai1,5103P$1.4/M$4.4/M$0.002

14GPT-5.5OpenAI1,4913P$5.0/M$30.0/M$0.012

15Gemini 3.7 FlashGoogle1,482$0.75/M$3.8/M$0.002

16Gemini 3.6 FlashGoogle1,422$0.75/M$3.8/M$0.002

17Muse Spark 1.1Meta1,381$1.3/M$4.3/M$0.002

18Gemini 3.5 FlashGoogle1,349$1.5/M$9.0/M$0.004

19Gemini 3.1 ProGoogle965$2.0/M$12.0/M$0.007

◆ 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: 19 models scored · 0 independently verified · 9 vendor cross-reference · 10 vendor-reported · 0 with source disagreement. How these tiers are assigned