Skip to contentT/TTokens or Towers

Compare

LeaderboardEvery tracked model, ranked and priced side by sideBenchmarksWhat each test measures and who leads itPricesAPI, media, and hardware rates with a cost calculator

Plan

Stack plannerSix questions to a priced local and hosted stackShortlistOur picks for subscriptions, APIs, and hardwareEnterpriseSeat plans against self-hosting for a whole team

Build

HardwareGPUs and workstations, and which models they fitHostsWhere to rent open-weight inference, and for how muchHarnessesCoding agents and the models they drive

Lab

FindingsResults from our own evaluationsScanAudit a repo’s AI usage in the browserMethodWhere the numbers come from and how we check them
Data checked September 25, 2026
Data checked September 25, 2026
Plan a stack
T/TTokens or Towers

An independent guide to AI models, what they cost, and the hardware to run them. No account, no API key, no sponsors.

Compare

  • Leaderboard
  • Benchmarks
  • Prices

Plan

  • Stack planner
  • Shortlist
  • Enterprise

Build

  • Hardware
  • Hosts
  • Harnesses

Lab

  • Findings
  • Scan
  • Method
Data checked September 25, 2026 · Every number links to its sourceRSS · Source on GitHub
Leaderboard/Ant Group
Ant Group

Ant Group · Ling 3.0

Ling 3.0 Flash

Open weightsGenerally availableNewMIT

Ant Group's open-weight 124B/5.1B-active text MoE reasoning model; the base of Ling-3.0-flash-VL.

AA Intelligence
24.9#57 of 142
Price
Self-host
Output speed
358tok/s
Context window
262K tokens

Composite indexes

  • Artificial Analysis Intelligence Index#57 of 142
    25independentv4.3.2 (AA estimate; independent evaluation forthcoming)Artificial Analysis: Ling 3.0 Flash ↗

    Leader: Claude Opus 5.5 at 58

Coding

  • Terminal-Bench 4.0#74 of 88
    0%independentAAArtificial Analysis: Ling 3.0 Flash ↗

    Leader: Claude Mythos 5.1 at 60.9%

  • Terminal-Bench 2.x#54 of 103
    55.4%independentAA, Terminal-Bench 2.1Artificial Analysis: Ling 3.0 Flash ↗

    Leader: Claude Fable 5.1 at 91.4%

  • SciCode#65 of 94
    42%independentAAArtificial Analysis: Ling 3.0 Flash ↗

    Leader: Claude Opus 5.5 at 66.9%

Reasoning and knowledge

  • Humanity’s Last Exam#63 of 147
    23.7%independentAA, no toolsArtificial Analysis: Ling 3.0 Flash ↗

    Leader: Claude Opus 5.5 at 61.4%

  • GPQA Diamond#58 of 142
    85.5%independentAAArtificial Analysis: Ling 3.0 Flash ↗

    Leader: GPT-6 Astra at 96.1%

  • CritPt#65 of 139
    1.7%independentAAArtificial Analysis: Ling 3.0 Flash ↗

    Leader: GPT-5.6 Sol at 32.3%

Vision and long context

  • AA Long Context Reasoning#68 of 139
    73%independentAAArtificial Analysis: Ling 3.0 Flash ↗

    Leader: Kimi K3 at 88.7%

Other published results

ResultScoreReported bySource
AA-Omniscience Index · AA-17.9 index (-100..100)independentArtificial Analysis: Ling 3.0 Flash ↗

Specs

Released
August 4, 2026
Parameters
124B total, 5.1B active
Size class
100 to 500B
Input
text
Output
text
Context
262K tokens
Max output
Not published
First token
2.49s
  • Speed: Artificial Analysis: Ling 3.0 Flash (InclusionAI first-party endpoint) ↗

Will it fit your budget?

The planner prices this model against local hardware and other APIs for your workload.

Plan a stack →

Compare with

  • xAIGrok 4.324.9
  • AlibabaQwen3.7-Plus25
  • Thinking Machines LabInkling25
  • Ant GroupLing-3.0-flash-VL24.6