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/Mistral
Mistral

Mistral · Magistral

Magistral Medium 1.2

Closed weightsDeprecatedproprietary

Mistral reasoning model; API retired 2026-07-31 with Mistral Medium 3.5 as the replacement.

AA Intelligence
11.8#89 of 142
Price
—
Output speed
—
Context window
128K tokens

Composite indexes

  • Artificial Analysis Intelligence Index#89 of 142
    12independentIntelligence Index v4.3; reasoning; estimatedArtificial Analysis: Magistral Medium 1.2 ↗

    Leader: Claude Opus 5.5 at 58

Coding

  • Terminal-Bench 2.x#90 of 103
    12.4%independentTerminal-Bench 2.1; reasoningArtificial Analysis: Magistral Medium 1.2 ↗

    Leader: Claude Fable 5.1 at 91.4%

  • LiveCodeBench#17 of 56
    75%independentreasoningArtificial Analysis: Magistral Medium 1.2 ↗

    Leader: Fugu at 92.9%

Agents and tool use

  • τ²-Bench#45 of 88
    52%independenttelecom; reasoningArtificial Analysis: Magistral Medium 1.2 ↗

    Leader: GLM-5.2 at 99.1%

  • GDPval-AA#95 of 103
    155independentreasoningArtificial Analysis: Magistral Medium 1.2 ↗

    Leader: Claude Opus 5.5 at 1846

Reasoning and knowledge

  • GPQA Diamond#92 of 142
    73.9%independentreasoningArtificial Analysis: Magistral Medium 1.2 ↗

    Leader: GPT-6 Astra at 96.1%

  • Humanity’s Last Exam#104 of 147
    10.3%independentno tools; reasoningArtificial Analysis: Magistral Medium 1.2 ↗

    Leader: Claude Opus 5.5 at 61.4%

  • CritPt#81 of 139
    0.3%independentreasoningArtificial Analysis: Magistral Medium 1.2 ↗

    Leader: GPT-5.6 Sol at 32.3%

Vision and long context

  • AA Long Context Reasoning#88 of 139
    53%independentreasoningArtificial Analysis: Magistral Medium 1.2 ↗

    Leader: Kimi K3 at 88.7%

  • MMMU-Pro#58 of 72
    59.7%independentreasoningArtificial Analysis: Magistral Medium 1.2 ↗

    Leader: Claude Opus 5.5 at 87.7%

Other published results

ResultScoreReported bySource
aime-2025 · AIME 2025; reasoning82%independentArtificial Analysis: Magistral Medium 1.2 ↗
Terminal-Bench Hard (AA) · reasoning12.9%independentArtificial Analysis: Magistral Medium 1.2 ↗
IFBench · reasoning43%independentArtificial Analysis: Magistral Medium 1.2 ↗
tau2-Bench Banking (AA) · reasoning5.6%independentArtificial Analysis: Magistral Medium 1.2 ↗
AA-Omniscience Index · reasoning-26.7 indexindependentArtificial Analysis: Magistral Medium 1.2 ↗

Specs

Released
September 18, 2025
Parameters
Undisclosed
Size class
Undisclosed
Input
text
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

    • PerplexitySonar Reasoning Pro (Sonar API)11.8
    • NVIDIANemotron Cascade 2 30B A3B11.7
    • OpenAIgpt-oss-120b11.6
    • ByteDanceSeed-OSS-36B-Instruct12.1