Inference
EN
InclusionAI

Ling 2.6 Flash

Ling 2.6 Flash is a standard model from InclusionAI in the Ling 2.6 family. 9 benchmarks count toward its index, in 5 categories.

  • Open weights
  • Standard
  • Input: text
  • Released 2026-04
RankedEnough results for an index.
IndexAll categories, out of 100.37.0±7.9Median 51.0
CoverageIndex weight that has results.75%
SpeedOutput tokens per second.104/sMedian 67/s
First tokenSeconds to the first output token.1.1 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.—Median $0.60
Output / 1MUS dollars per 1M output tokens.—Median $2.55
ContextMaximum tokens in one request.262KMedian 262K
EloLMArena rating and rank.—Median 1422

Run locally

107.49B parameters
16-bit
226.7 GB
8-bit
120.9 GB
4-bit
69.4 GB
Weights
Hugging Face (opens in a new tab) ↗

Memory need with a short context. The 4-bit copy fits in 128 GB. Compare local models

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.2 counted46.9156 / 218
CodingCode writing and repair.1 counted31.0—
ReasoningLogic problems and puzzles.2 counted32.8198 / 227
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.3 counted30.8237 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.1 counted42.5—
MathMath problems.None counted——

Results

9 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
τ²-Bench Tool-Agent-User EvaluationAgenticAbove fitFar above this model's index.86.0%54 / 149
Artificial Analysis IFBenchInstruction57.4%67 / 146
Critical Physics TasksReasoning0.0%150 / 214
Artificial Analysis Humanity's Last ExamKnowledge6.3%168 / 222
GDPval-AA normalizedAgentic0.0%101 / 133
Artificial Analysis GPQA DiamondKnowledge59.3%157 / 199
Graduate-Level Google-Proof Q&AKnowledge59.0%113 / 141
Instruction Following BenchmarkInstruction57.0%46 / 57
Artificial Analysis Long Context ReasoningReasoning31.3%179 / 217
Artificial Analysis Omniscience AccuracyKnowledge15.6%149 / 164
Scientific Code BenchmarkCoding27.0%33 / 35

Sources

BenchLMCC BY-NC 4.0

History

5 releases
Index37.6 → 37.0
23 Oct 202612 Nov 2026

Questions

How good is Ling 2.6 Flash?
Its index is 37.0 out of 100. That is place 228 of 283 ranked models.
What is Ling 2.6 Flash best at?
Agentic: 46.9 out of 100, place 156 of 218.
How fast is Ling 2.6 Flash?
104 output tokens per second, 1.1 s to the first token.
What is the context window of Ling 2.6 Flash?
262K tokens.
Is Ling 2.6 Flash open source?
Yes. Its weights are published.
When was Ling 2.6 Flash released?
April 2026.

Badge

Ling 2.6 Flash on Inference360: place 228 of 283, index 37.0
HTML
<a href="https://inference360.ai/models/ling-2-6-flash"><img src="https://inference360.ai/badges/ling-2-6-flash.svg" alt="Ling 2.6 Flash on Inference360: place 228 of 283, index 37.0" height="20"></a>
Markdown
[![Ling 2.6 Flash on Inference360: place 228 of 283, index 37.0](https://inference360.ai/badges/ling-2-6-flash.svg)](https://inference360.ai/models/ling-2-6-flash)

Compare with

Nemotron 3.5 Lightning 30B A3B NVFP437.0MiniCPM5-2B37.1Sarvam 105B36.7QwQ-32B36.3

More from InclusionAI

All models
LLaDA2.2-mini24.3LLaDA2.2-flashUnrankedLing 3.0 Flash50.9Ling 3.0 Flash FP8UnrankedLing 3.0 TinyUnranked