Skip to content
llmwaves

Ling-3.0-flash

InclusionAI · released Jul 23, 2026

Open weightsReasoningTool use

*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...

Specification

Context window
262K
Max output
33K
Knowledge cutoff
Not stated
Parameters
127.5B
Licence
mit
Serving providers
2
Moderated
No
Uptime
100.0%

Intelligence

37.8

85th percentile

Coding

50.6

Coding Index

Agentic

Agentic Index

Output speed

211 t/s

Median across providers

Latency

293ms

Time to first token

Cost per task

$0.006

Estimated

Benchmarks

Where the score comes from

The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.

Evaluation scores

Percentage correct · higher is better

  • GPQA Diamond
    85.5%
  • AA-LCR (long context)
    67.0%
  • SciCode
    41.1%
  • τ²-bench (Telecom)
    27.2%
  • Humanity's Last Exam
    23.7%

An evaluation missing from this list was not run for this model — it is not a zero.

View as table
EvaluationScore
GPQA Diamond85.5%
AA-LCR (long context)67.0%
SciCode41.1%
τ²-bench (Telecom)27.2%
Humanity's Last Exam23.7%

Against its peers

Intelligence Index · this model highlighted, nearest peers in grey

Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.

View as table
ModelIntelligence
MiMo-V2.538.0
Grok 4.2038.0
Grok 4.337.9
Ling-3.0-flash37.8
Qwen3.6 27B37.7
GPT-5.137.5
Gemini 3.5 Flash Lite37.4
Claude Sonnet 4.636.8

Percentile among all indexed models

Intelligence85th
Coding65th

Pricing

What it costs to run

List prices per million tokens, plus what one representative task works out to.

List price

Input / 1M tokens
$0.021
Output / 1M tokens
$0.063
Cached input / 1M
$0.004
Blended 3:1
$0.032

One task, estimated

$0.006

Input tokens
50,000
Output tokens
80,000
Profile
Reasoning

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).

Serving providers

Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.