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/OpenAI
OpenAI

OpenAI · GPT-5.6

GPT-5.6 Terra

Closed weightsSupersededproprietary

Mid-sized GPT-5.6 model still offered via API; GPT-6 has no Terra tier.

AA Intelligence
42.1#16 of 142
Input / output per 1M
$2.00/ $12.00
Output speed
92tok/s
Context window
1.05M tokens

Composite indexes

  • Artificial Analysis Intelligence Index#16 of 142
    42independentAA Intelligence Index v4.3.2, max effortArtificial Analysis: GPT-5.6 Terra (max) ↗

    Leader: Claude Opus 5.5 at 58

Coding

  • Terminal-Bench 4.0#11 of 88
    35.4%independentTerminal-Bench 4.0 (AA harness), max effortArtificial Analysis: GPT-5.6 Terra (max) ↗

    Leader: Claude Mythos 5.1 at 60.9%

  • Terminal-Bench 2.x#9 of 103
    88%independentTerminal-Bench 2.1 (AA harness), max effortArtificial Analysis: GPT-5.6 Terra (max) ↗

    Leader: Claude Fable 5.1 at 91.4%

  • SciCode#21 of 94
    55%independentmax effortArtificial Analysis: GPT-5.6 Terra (max) ↗

    Leader: Claude Opus 5.5 at 66.9%

Agents and tool use

  • GDPval-AA#26 of 103
    1432independentGDPval-AA, max effortArtificial Analysis: GPT-5.6 Terra (max) ↗

    Leader: Claude Opus 5.5 at 1846

  • τ²-Bench#24 of 88
    86.3%independenttelecom (AA), max effortArtificial Analysis: GPT-5.6 Terra (max) ↗

    Leader: GLM-5.2 at 99.1%

Reasoning and knowledge

  • Humanity’s Last Exam#23 of 147
    42.9%independentno tools (AA), max effortArtificial Analysis: GPT-5.6 Terra (max) ↗

    Leader: Claude Opus 5.5 at 61.4%

  • GPQA Diamond#21 of 142
    92.5%independentAA, max effortArtificial Analysis: GPT-5.6 Terra (max) ↗

    Leader: GPT-6 Astra at 96.1%

  • CritPt#5 of 139
    30%independentmax effortArtificial Analysis: GPT-5.6 Terra (max) ↗

    Leader: GPT-5.6 Sol at 32.3%

  • ARC-AGI-2#9 of 25
    83.9%independentsemi-private, MaxARC Prize leaderboard ↗

    Leader: GPT-6 Astra at 95%

  • ARC-AGI-3#7 of 9
    0.8%independentsemi-private, MaxARC Prize leaderboard ↗

    Leader: GPT-6 Astra at 62.7%

Vision and long context

  • AA Long Context Reasoning#13 of 139
    83%independentmax effortArtificial Analysis: GPT-5.6 Terra (max) ↗

    Leader: Kimi K3 at 88.7%

  • MMMU-Pro#13 of 72
    80.7%independentAA, max effortArtificial Analysis: GPT-5.6 Terra (max) ↗

    Leader: Claude Opus 5.5 at 87.7%

Human preference

  • LMArena Text#23 of 54
    1466independentgpt-5.6-terra-xhigh, style control default, vote cutoff 2026-09-13LMArena Text leaderboard ↗

    Leader: Claude Fable 5 at 1506

  • LMArena WebDev#32 of 54
    1519independentgpt-5.6-terra-xhigh, LMArena Code arena (formerly WebDev), vote cutoff 2026-09-23LMArena Code (WebDev) leaderboard ↗

    Leader: Claude Opus 5.5 at 1818

Other published results

ResultScoreReported bySource
AA-Omniscience Index · max effort0.1 index (-100 to 100)independentArtificial Analysis: GPT-5.6 Terra (max) ↗
AutomationBench-AA (partial score) · max effort59.6%independentArtificial Analysis: GPT-5.6 Terra (max) ↗
Terminal-Bench Science (AA) · max effort13.8%independentArtificial Analysis: GPT-5.6 Terra (max) ↗

Specs

Released
July 9, 2026
Parameters
Undisclosed
Size class
Undisclosed
Input
text, image
Output
text
Context
1.05M tokens
Max output
128K tokens
Cached input
$0.20 / 1M
Blended 70/30
$5.00 / 1M
First token
167.80s
  • Price: OpenAI API pricing ↗ Standard, short context. Long context $4/$18. No GPT-6 Terra exists.
  • Speed: Artificial Analysis: GPT-5.6 Terra (max) (median output speed; TTFT is time to first chunk incl. reasoning) ↗

Will it fit your budget?

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

Plan a stack →

Compare with

  • Z.aiGLM-5.3-Flash42
  • AnthropicClaude Opus 4.841.8
  • GoogleGemini 3.8 Flash40.9
  • StepFunStep 5 Preview43.7