Ling-2.6-1T

Released 2026-04 · chat · Not published · 0 benchmarks · Open weight

Editorial notes

Lanzado por inclusionAI (lab de Ant Group), abril 2026. Hermano NON-reasoning ("fast thinking") de Ring-2.6-1T — misma escala MoE 1T total / 63B activos, open-weight MIT. Optimizado para respuesta directa de alto throughput (sin cadena de razonamiento extendida). Artificial Analysis Intelligence Index 31→26 (tercero). Ant NO publica benchmarks individuales del core-set para Ling (solo el indice compuesto de AA) — por eso no rankea: sin GPQA-D/SWE-V/AIME individuales no alcanza el gate. Context y pricing no confirmados al 2026-06-16 (comparte arquitectura con Ring pero el card de Ling no los lista por separado). No confundir sus numeros con los de Ring (el AIME 2026 95.83 / GPQA-D 88.27 que circulan son de Ring, reasoning).

Spec sheet

Company: Ant Group
Country: CN
Type: chat
Release: 2026-04
Context: Not published
Params total: 1.0T
Params active (MoE): 63B
License: mit
Slug: ling-2-6-1t

No scores published for this model. The editorial notes have additional context.

Cite this model

BibTeX · APA

BibTeX

@misc{frontier-ling-2-6-1t,
  title  = {Ling-2.6-1T},
  author = {{Ant Group}},
  year   = {2026},
  note   = {Frontier Benchmarks AI atlas. Accessed 2026-06-17},
  url    = {https://frontierbenchmarks.com/models/ling-2-6-1t}
}

APA

Ant Group (2026). Ling-2.6-1T [Large language model]. Frontier Benchmarks AI. Retrieved 2026-06-17, from https://frontierbenchmarks.com/models/ling-2-6-1t

Citation reflects the atlas page, not the original model paper. For the paper, see the "Resources" section above.

Battle vs another model ← All models More from Ant Group Methodology