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/Alibaba
Alibaba

Alibaba · Qwen3.7

Qwen3.7-Plus

Closed weightsGenerally availableproprietary

Mid-tier hosted multimodal Qwen and still the newest Plus model. Parameter counts (397B/17B) come from the Qwen3.8-Flash-Next comparison table.

AA Intelligence
25#54 of 142
Input / output per 1M
$0.40/ $1.60
Output speed
70tok/s
Context window
1M tokens

Composite indexes

  • Artificial Analysis Intelligence Index#54 of 142
    25independentv4.3.2, reasoningArtificial Analysis: Qwen3.7 Plus ↗

    Leader: Claude Opus 5.5 at 58

Coding

  • Terminal-Bench 4.0#44 of 88
    1%independentreasoning, AA-runArtificial Analysis: Qwen3.7 Plus ↗

    Leader: Claude Mythos 5.1 at 60.9%

  • Terminal-Bench 2.x#46 of 103
    61%independentTerminal-Bench 2.1, reasoning, AA-runArtificial Analysis: Qwen3.7 Plus ↗

    Leader: Claude Fable 5.1 at 91.4%

  • SciCode#53 of 94
    46.1%independentreasoning, AA-runArtificial Analysis: Qwen3.7 Plus ↗

    Leader: Claude Opus 5.5 at 66.9%

  • SWE-bench Pro#17 of 31
    57.6%vendorQwen3.7-Plus column in the Qwen3.8-27B cardQwen3.8-27B model card (Hugging Face) ↗

    Leader: Claude Opus 5.5 at 89.9%

Agents and tool use

  • τ²-Bench#15 of 88
    93%independenttelecom, reasoning, AA-runArtificial Analysis: Qwen3.7 Plus ↗

    Leader: GLM-5.2 at 99.1%

  • GDPval-AA#65 of 103
    756independentGDPval-AA v2.1, reasoningArtificial Analysis: Qwen3.7 Plus ↗

    Leader: Claude Opus 5.5 at 1846

  • OSWorld-Verified#9 of 16
    73.3%vendorOSWorld-Verified, Qwen3.7-Plus column in the Qwen3.8-27B cardQwen3.8-27B model card (Hugging Face) ↗

    Leader: Kimi K3 at 84.8%

Reasoning and knowledge

  • GPQA Diamond#39 of 142
    90.3%vendorQwen3.7-Plus column in the Qwen3.8-27B cardQwen3.8-27B model card (Hugging Face) ↗
    90%independentreasoning, AA-runArtificial Analysis: Qwen3.7 Plus ↗

    Leader: GPT-6 Astra at 96.1%

  • Humanity’s Last Exam#46 of 147
    35.6%independentreasoning, no tools, AA-runArtificial Analysis: Qwen3.7 Plus ↗

    Leader: Claude Opus 5.5 at 61.4%

  • CritPt#44 of 139
    9.1%independentreasoning, AA-runArtificial Analysis: Qwen3.7 Plus ↗

    Leader: GPT-5.6 Sol at 32.3%

Vision and long context

  • AA Long Context Reasoning#65 of 139
    73%independentreasoning, AA-LCRArtificial Analysis: Qwen3.7 Plus ↗

    Leader: Kimi K3 at 88.7%

  • MMMU-Pro#14 of 72
    80.5%independentreasoning, AA-runArtificial Analysis: Qwen3.7 Plus ↗

    Leader: Claude Opus 5.5 at 87.7%

Human preference

  • LMArena Text#29 of 54
    1456independentarena entry "qwen3.7-plus", 39,334 votes, checked 2026-09-25Arena (LMArena) text leaderboard ↗

    Leader: Claude Fable 5 at 1506

Other published results

ResultScoreReported bySource
IFBench (AA) · reasoning78%independentArtificial Analysis: Qwen3.7 Plus ↗
Terminal-Bench Hard (AA) · reasoning47%independentArtificial Analysis: Qwen3.7 Plus ↗

Specs

Released
June 1, 2026
Parameters
397B total, 17B active
Size class
100 to 500B
Input
text, image, video
Output
text
Context
1M tokens
Max output
131K tokens
Cached input
$0.08 / 1M
Blended 70/30
$0.76 / 1M
First token
2.23s
  • Price: Alibaba Cloud Model Studio pricing (Singapore / International) ↗ List rate for 0-256K input (thinking and non-thinking output both $1.6); 256K-1M is $1.2 in / $4.8 out. A limited-time 20% discount currently brings 0-256K to $0.32 / $1.28. Alias = qwen3.7-plus-2026-05-26. Cached = implicit cache list rate per https://www.qwencloud.com/models/qwen3.7-plus. No Qwen3.8-Plus exists yet.
  • Speed: Artificial Analysis: Qwen3.7 Plus ↗

Will it fit your budget?

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

Plan a stack →

Compare with

  • Thinking Machines LabInkling25
  • xAIGrok 4.324.9
  • Ant GroupLing 3.0 Flash24.9
  • XiaomiMiMo-V2.525.2