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/Ai2
Ai2

Ai2 · Molmo 2

Molmo 2 8B

Open weightsGenerally availableApache 2.0

Ai2's open 8B vision-language model with image and video input.

AA Intelligence
5#140 of 142
Price
Self-host
Output speed
—
Context window
37K tokens

Composite indexes

  • Artificial Analysis Intelligence Index#140 of 142
    5independentIntelligence Index v4.3; non-reasoning; estimatedArtificial Analysis: Molmo2-8B ↗

    Leader: Claude Opus 5.5 at 58

Agents and tool use

  • τ²-Bench#87 of 88
    0%independenttelecom; non-reasoningArtificial Analysis: Molmo2-8B ↗

    Leader: GLM-5.2 at 99.1%

Reasoning and knowledge

  • GPQA Diamond#133 of 142
    42.5%independentnon-reasoningArtificial Analysis: Molmo2-8B ↗

    Leader: GPT-6 Astra at 96.1%

  • Humanity’s Last Exam#135 of 147
    4.3%independentno tools; non-reasoningArtificial Analysis: Molmo2-8B ↗

    Leader: Claude Opus 5.5 at 61.4%

  • CritPt#127 of 139
    0%independentnon-reasoningArtificial Analysis: Molmo2-8B ↗

    Leader: GPT-5.6 Sol at 32.3%

Vision and long context

  • AA Long Context Reasoning#134 of 139
    0%independentnon-reasoningArtificial Analysis: Molmo2-8B ↗

    Leader: Kimi K3 at 88.7%

  • MMMU-Pro#71 of 72
    37.5%independentnon-reasoningArtificial Analysis: Molmo2-8B ↗

    Leader: Claude Opus 5.5 at 87.7%

Other published results

ResultScoreReported bySource
Terminal-Bench Hard (AA) · non-reasoning0%independentArtificial Analysis: Molmo2-8B ↗
IFBench · non-reasoning26.9%independentArtificial Analysis: Molmo2-8B ↗
AA-Omniscience Index · non-reasoning-69.2 indexindependentArtificial Analysis: Molmo2-8B ↗

Specs

Released
December 11, 2025
Parameters
8.7B
Size class
Under 10B
Input
text, image, video
Output
text
Context
37K 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

    • Swiss AI InitiativeApertus 70B Instruct5.1
    • MistralMinistral 3 3B4.8
    • CohereTiny Aya Global4.8
    • AI21 LabsJamba 1.7 Mini5.2