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/Meituan
Meituan

Meituan · LongCat Flash

LongCat Flash Lite

Open weightsDeprecatedMIT

Small open-weight LongCat MoE (68.5B/3B active); retired from Meituan's API on 2026-05-29 but weights remain available.

AA Intelligence
11.5#93 of 142
Price
Self-host
Output speed
—
Context window
256K tokens

Composite indexes

  • Artificial Analysis Intelligence Index#93 of 142
    12independentv4.3.2 (AA estimate; independent evaluation forthcoming)Artificial Analysis: LongCat Flash Lite ↗

    Leader: Claude Opus 5.5 at 58

Agents and tool use

  • τ²-Bench#33 of 88
    79.5%independentAA, telecomArtificial Analysis: LongCat Flash Lite ↗

    Leader: GLM-5.2 at 99.1%

Reasoning and knowledge

  • Humanity’s Last Exam#117 of 147
    5.8%independentAA, no toolsArtificial Analysis: LongCat Flash Lite ↗

    Leader: Claude Opus 5.5 at 61.4%

  • GPQA Diamond#108 of 142
    63.6%independentAAArtificial Analysis: LongCat Flash Lite ↗

    Leader: GPT-6 Astra at 96.1%

  • CritPt#101 of 139
    0%independentAAArtificial Analysis: LongCat Flash Lite ↗

    Leader: GPT-5.6 Sol at 32.3%

Vision and long context

  • AA Long Context Reasoning#106 of 139
    28.3%independentAAArtificial Analysis: LongCat Flash Lite ↗

    Leader: Kimi K3 at 88.7%

Other published results

ResultScoreReported bySource
Terminal-Bench Hard (AA) · AA10.6%independentArtificial Analysis: LongCat Flash Lite ↗
IFBench (AA) · AA43.1%independentArtificial Analysis: LongCat Flash Lite ↗
AA-Omniscience Index · AA-70.1 index (-100..100)independentArtificial Analysis: LongCat Flash Lite ↗

Specs

Released
January 28, 2026
Parameters
68.5B total, 3B active
Size class
40 to 100B
Input
text
Output
text
Context
256K tokens
Max output
Not published

    Will it fit your budget?

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

    Plan a stack →

    Compare with

    • OpenAIgpt-oss-120b11.6
    • MistralMistral Small 411.3
    • NVIDIANemotron Cascade 2 30B A3B11.7
    • MistralMagistral Medium 1.211.8