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/ServiceNow
ServiceNow

ServiceNow · Apriel

Apriel v1.6 15B Thinker

Open weightsGenerally availableMIT

ServiceNow's 15B open-weights multimodal reasoning model for enterprise and single-GPU deployment.

AA Intelligence
13.4#83 of 142
Price
Self-host
Output speed
—
Context window
128K tokens

Composite indexes

  • Artificial Analysis Intelligence Index#83 of 142
    13independentIntelligence Index v4.3; reasoning; estimatedArtificial Analysis: Apriel-v1.6-15B-Thinker ↗

    Leader: Claude Opus 5.5 at 58

Coding

  • LiveCodeBench#9 of 56
    80.7%independentreasoningArtificial Analysis: Apriel-v1.6-15B-Thinker ↗

    Leader: Fugu at 92.9%

Agents and tool use

  • τ²-Bench#37 of 88
    69.3%independenttelecom; reasoningArtificial Analysis: Apriel-v1.6-15B-Thinker ↗

    Leader: GLM-5.2 at 99.1%

Reasoning and knowledge

  • GPQA Diamond#94 of 142
    73.3%independentreasoningArtificial Analysis: Apriel-v1.6-15B-Thinker ↗

    Leader: GPT-6 Astra at 96.1%

  • Humanity’s Last Exam#101 of 147
    10.8%independentno tools; reasoningArtificial Analysis: Apriel-v1.6-15B-Thinker ↗

    Leader: Claude Opus 5.5 at 61.4%

  • CritPt#87 of 139
    0.3%independentreasoningArtificial Analysis: Apriel-v1.6-15B-Thinker ↗

    Leader: GPT-5.6 Sol at 32.3%

Other published results

ResultScoreReported bySource
aime-2025 · AIME 2025; reasoning88%independentArtificial Analysis: Apriel-v1.6-15B-Thinker ↗
Terminal-Bench Hard (AA) · reasoning14.4%independentArtificial Analysis: Apriel-v1.6-15B-Thinker ↗
IFBench · reasoning69.1%independentArtificial Analysis: Apriel-v1.6-15B-Thinker ↗
AA-Omniscience Index · reasoning-59.4 indexindependentArtificial Analysis: Apriel-v1.6-15B-Thinker ↗

Specs

Released
November 25, 2025
Parameters
15B
Size class
10 to 40B
Input
text, image
Output
text
Context
128K 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

    • AmazonAmazon Nova 2 Lite13.4
    • AmazonAmazon Nova 2 Omni (Preview)13.6
    • CohereCommand A+13.1
    • NVIDIANemotron 3.5 Lightning 30B A3B12.9