Se connecter
MAI-Code-1-Flash logo

MAI-Code-1-Flash

Microsoft · Sorti juin 2026

Voir les tarifsComparer les modèles
Conditionnel

MAI-Code-1-Flash was Microsoft's first in-house coding model, a sparse MoE priced at $0.75/$4.50 per 1M tokens. GitHub retired it from Copilot on 10 September 2026 and names MAI-Code-1.1-Flash, at $0.20/$1.20, as the replacement; it no longer appears in Copilot's supported-models or pricing tables. Copilot users should switch to 1.1-Flash, which is cheaper and scores higher on Terminal-Bench 2.1.

Est-ce fait pour vous ?

Recommandé pour

  • Historical comparison only: GitHub retired it from Copilot on 10 September 2026, so new Copilot work should use MAI-Code-1.1-Flash
  • Fast, iterative agentic coding workflows where latency and token cost matter more than frontier reasoning, on any host that still serves it

Déconseillé pour

  • New Copilot workflows: the model no longer appears in GitHub Copilot's supported-models or pricing tables after its 10 September 2026 retirement
  • Cost-sensitive teams: its successor MAI-Code-1.1-Flash lists at $0.20/$1.20 per 1M against this model's $0.75/$4.50
  • Complex multi-file architectural changes or novel algorithm design requiring frontier-level code reasoning
  • General-purpose non-coding tasks — this is a specialized coding model, not a general assistant

Performances par tâche

Complétion de code et autocomplétion

Excellent

Excellent — faible latence, longueur de réponse adaptative, conçu pour la boucle interactive de Copilot

Refactorisation de code

Very Good

Solide — gère bien le refactoring routinier ; 60% de tokens en moins que les concurrents sur SWE-Bench Verified

Suivi d'instructions (codage)

Excellent

Meilleur de sa catégorie pour le niveau léger — +28,9 points sur IF Bench vs Haiku 4.5 ; 85,8% en raisonnement adversarial

Utilisation d'outils agentiques (Copilot)

Very Good

Solide — entraîné avec le harnais de production Copilot ; bat Haiku 4.5 sur τ¹-Bench

Corrections de bugs réels (SWE-Bench Pro)

Good

Solide pour sa taille — 51,2% de taux de réussite ; 16 points d'avance sur Haiku 4.5 mais bien en dessous des modèles frontière

Architecture multi-fichiers / conception nouvelle

Fair

Faible — 5B paramètres actifs limitent la profondeur de raisonnement ; utilisez un modèle flagship pour le travail complexe

Raisonnement mathématique et scientifique

Very Good

Bon — 92,5% AIME 2026, 84,6% GPQA Diamond ; solide pour un modèle léger

Chat généraliste / non-codage

Poor

Pas conçu pour cela — un modèle de codage spécialisé ; utilisez GPT-5.5 ou Claude pour les tâches générales

Tarifs

Entrée

$0.75 / 1M tokens

Sortie

$4.50 / 1M tokens

Contexte

Retired from Copilot Sep 10 2026; 256K ctx

Voir tous les tarifs

Tests de performance

TestScoreSource
SWE-Bench Pro51.2% (vs Haiku 4.5: 35.2%) Source
SWE-Bench VerifiedBeats Haiku 4.5 with up to 60% fewer tokens Source
AIME 202692.5% (vs Haiku 4.5: 83.3%) Source
GPQA Diamond84.6% (vs Haiku 4.5: 73.2%) Source
IF Bench75.0 (vs Haiku 4.5: 46.1) Source
Adversarial reasoning85.8% adjusted accuracy Source
Frontier Math (Tier 1-3)6.3% (vs Haiku 4.5: 2.8%) Source
Frontier Science58.2% (vs Haiku 4.5: 42.3%) Source
HLE18.0% (vs Haiku 4.5: 9.5%) Source

Historique des verdicts

26 sept. 2026
conditional -> conditional (summary corrected: retired from Copilot): rating_before=conditional, rating_after=conditional. The summary still called it the model for high-volume Copilot workflows. GitHub's changelog set its deprecation for 2026-09-10, and on 2026-09-26 it is absent from Copilot's supported-models and pricing tables. The rating is held pending an operator ruling, since a retired model may merit caution or avoid.
15 juil. 2026
copy edit to brevity standard: detail preserved in existing structured children

Sources

Journal de vérification

  • Tarifs· Aucun changement

    Agent automatisé

  • Tarifs· Aucun changement

    Agent automatisé

  • Statut· Mis à jour

    Agent automatisé

    GitHub's changelog set MAI-Code-1-Flash's deprecation for 2026-09-10 and names MAI-Code-1.1-Flash as the replacement. On 2026-09-26 the model is absent from both the Copilot models-and-pricing table and the supported-models table, while MAI-Code-1.1-Flash is listed GA at $0.20/$1.20. Fixed via model_update: pricing_context is now 'Retired from Copilot Sep 10 2026; 256K ctx'; strengths and audiences were rewritten to drop the 'all Copilot tiers' and 'stretch Copilot credits' claims and to point to 1.1-Flash; the changelog and both GitHub docs pages were added as sources. The summary was corrected via verdict_set e9dd3180, rating_before=conditional and rating_after=conditional; the rating is held pending an operator ruling. Price scalars are unchanged. No draft post: the retirement was announced on 2026-08-11 and took effect 16 days ago.

  • Tarifs· Aucun changement

    Agent automatisé

  • Tarifs· Aucun changement

    Agent automatisé

  • Tarifs· Aucun changement

    Agent automatisé

  • Tarifs· Aucun changement

    Agent automatisé

  • Tarifs· Aucun changement

    Agent automatisé

  • Tarifs· Aucun changement

    Agent automatisé

    Pricing unchanged: $0.75/$4.50 per 1M tokens, 256K context. Confirmed live on GitHub Copilot pricing page.

  • Tarifs· Aucun changement

    Importé au lancement

  • Profil· Aucun changement

    Importé au lancement

Comment nous évaluons