Additional Insights on Inkling Efficiency and Scores
ArtificialAnlys · x · 2026-07-16
This reply shares further key benchmark data for Inkling:
- GDPval-AA v2 Elo is 1238, beating Kimi K.6 and DeepSeek v4 Flash max
- Token efficiency: Averages around 25K output tokens per Intelligence Index task, fewer than GLM-5.2, Kimi K2.6, and DeepSeek v4 Pro
This remains a breakdown of Inkling's overall performance.
More from Models
- Mocked benchmark shows DeepSeek's document chart grounding badly misaligned — burkov · 2026-10-18
- Dev complains Claude's habit of saying "not done" is his biggest pain point — jasonkneen · 2026-10-18
- Open-weight TYGER speech decision model makes 80ms turn-taking calls for full-duplex voice agents — solyarisoftware · 2026-10-18
- Paying Google AI subscriber blocked: custom-domain Workspace accounts can't access AI Studio — ChrisRackauckas · 2026-10-18
- Running Ling 3.1 Flash (560B MoE, 25B Active) Across 4 DGX Sparks via llama.cpp RPC — BerryBlush_Rogers691 · 2026-10-18
- Users press OpenAI on long-delayed Adult Mode a year after it was promised — ___Patrice___ · 2026-10-18