Models/Ling 2.6 Flash

MDL

Ling 2.6 Flash

InclusionAI

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$0.1 / $0.3

in / out

Context

262.1K

tokens

Avg score

40.3

7 benchmarks

AA Intelligence

14.1

index

Speed

181 tok/s

TTFT 0.7s

Released

Apr 21, 2026

About

Ling 2.6 Flash is a proprietary model in the Ling family from InclusionAI. Benchmarked on 7 evals, averaging 40.3.

Benchmark scores · 7

avg 40.3 — higher is better

τ²-benchartificial-analysis · 2026-07

GPQA Diamondartificial-analysis · 2026-07

59.3

IFBenchartificial-analysis · 2026-07

57.4

SciCodeartificial-analysis · 2026-07

27.1

AA Long-Context Reasoningartificial-analysis · 2026-07

Terminal-Bench Hardartificial-analysis · 2026-07

21.2

Humanity's Last Examartificial-analysis · 2026-07

6.2

The research behind this model

all papers mentioning it →

Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale▲ 87 on HF · Jun 13, 2026

Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.

Details

PublisherInclusionAI

FamilyLing

Parameters—

License—

WeightsClosed

ReleasedApr 21, 2026

Performance & price

Output speed181 tok/s

Latency (TTFT)0.7s

Price in / out$0.1 / $0.3 per 1M

Blended price$0.15 / 1M

Coding index25.3

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

History

full ledger →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers

Artificial Analysis$0.3/M