Atlas

Models

← All models

Ling 2.6 1T

InclusionAI · 2026-04-29 · 1T parameters

Ling 2.6 1T is InclusionAI's open-weight instant/instruct MoE flagship, released on April 29, 2026; the official checkpoint contains exactly 1,025,657,871,744 parameters, while InclusionAI describes its activated size only approximately as 63B. It upgrades the Ling 2.0 base through architectural migration and about 9.6T tokens of additional pre-training, combining Lightning Attention and MLA in a 7:1 ratio with a native 262,144-token limit. Post-training emphasizes fast, token-efficient answers and agentic coding and tool-use workflows, making it the instant-response counterpart to the deeper-reasoning Ring 2.6 1T.

Benchmark scores

BenchmarkScore
AA-LCR34.7
AA-Omniscience Index-51.0
ALE-Bench1108
Artificial Analysis Intelligence Index26.1
Artificial Analysis Omniscience Accuracy21.4
Artificial Analysis Omniscience Hallucination Rate92.2
Artificial Analysis Openness Index38.9
BuseyBench SVG2.3
Capability138.9
CritPt0.3
Extended NYT Connections 940-Puzzle Set10.8
Extended NYT Connections Newest 10013.0
GBENCH One-shot Coding GScore22.3
GPQA Diamond75.2
Humanity's Last Exam (Text-Only)8.2
IFBench (Artificial Analysis)56.9
SciCode (Artificial Analysis)37.0
SnakeBench Average Apples7.5
SnakeBench Best Apples20.0
SnakeBench Rating24.9
SnakeBench Total Apples75.0
SnakeBench Win Rate70.0
Terminal-Bench Hard31.1
τ²-bench (Telecom)89.8
Loading Atlas data…