# MAI Code 2 Benchmark Scores & Performance

> MAI Code 2 by Microsoft has 3 source-displayable benchmark rows but no public overall score. It remains unranked.

Canonical page: https://benchlm.ai/models/mai-code-2

Last updated: November 17, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Microsoft |
| Source Type | Proprietary |
| Reasoning Type | Reasoning |
| Context Window | 1.05M |
| Official model card | [Microsoft AI MAI Code 2 and MAI Code 2 Flash model card](https://microsoft.ai/pdf/MAI-Code-2-And-MAI-Code-2-Flash-Model-Card.pdf) |
| Overall Score | Not computed (unranked) |
| Overall Rank | Unranked |

## Family & Coverage

- Family: MAI-Code
- Variant: base
- Benchmarks covered: 3 of 818
- Sibling models: [MAI Code 2 Flash](/models/mai-code-2-flash), [MAI-Code-1.1-Flash](/models/mai-code-1-1-flash)
- Coverage note: Published evidence is shown below; no public overall score is assigned.

## Agentic Benchmarks

| Benchmark | Score | Who ran it | Source |
|-----------|-------|------------|--------|
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 84.6% | Reported by Microsoft | [Microsoft AI: MAI Code 2 and MAI Code 2 Flash model card](https://microsoft.ai/pdf/MAI-Code-2-And-MAI-Code-2-Flash-Model-Card.pdf) |

## Coding Benchmarks

| Benchmark | Score | Who ran it | Source |
|-----------|-------|------------|--------|
| [DeepSWE](/benchmarks/deepswe) | 73.2% | Reported by Microsoft | [Microsoft AI: MAI Code 2 and MAI Code 2 Flash model card](https://microsoft.ai/pdf/MAI-Code-2-And-MAI-Code-2-Flash-Model-Card.pdf) |
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 84.6% | Reported by Microsoft | [Microsoft AI: MAI Code 2 and MAI Code 2 Flash model card](https://microsoft.ai/pdf/MAI-Code-2-And-MAI-Code-2-Flash-Model-Card.pdf) |

## Lab-reported results

Microsoft published this result with a metric, split or setting no scored field uses, or for a test with no BenchLM page. They are shown for reference and never count toward a rank.

| Benchmark | Reported value | What was measured | Who ran it | Use in ranking | Source |
|-----------|----------------|-------------------|------------|----------------|--------|
| SWE Atlas | 43.1% | Pass rate · Microsoft's MSBench runs with the GitHub Copilot CLI harness (v1.0.102, no subagents), max reasoning effort, mean of three runs; 284 tasks across codebase Q&A, test writing and refactoring | Reported by Microsoft | Shown only | [Microsoft AI MAI Code 2 and MAI Code 2 Flash model card](https://microsoft.ai/pdf/MAI-Code-2-And-MAI-Code-2-Flash-Model-Card.pdf) |

## Other Microsoft Models

- [Phi-4](/models/phi-4) - Score: 22.7
- [MAI-Thinking-1](/models/mai-thinking-1) - Score: not computed
- [Phi-3.5-mini](/models/phi-3-5-mini) - Score: not computed
- [Phi-4-reasoning-plus](/models/phi-4-reasoning-plus) - Score: not computed
- [Phi-4-reasoning](/models/phi-4-reasoning) - Score: not computed
- [MAI Code 2 Flash](/models/mai-code-2-flash) - Score: not computed
- [MAI-Code-1.1-Flash](/models/mai-code-1-1-flash) - Score: not computed
- [Raw Phi-4 mini direct logits](/models/raw-phi-4-mini) - Score: not computed
- [Fara1.5-27B](/models/fara-1-5-27b) - Score: not computed
- [Fara1.5-4B](/models/fara-1-5-4b) - Score: not computed
- [Microsoft-Decision-1](/models/microsoft-decision-1) - Score: not computed
- [MAI-Transcribe-2-Streaming](/models/mai-transcribe-2-streaming) - Score: not computed
- [MAI-Voice-2.1](/models/mai-voice-2-1) - Score: not computed
- [MAI-Voice-2.1-Flash](/models/mai-voice-2-1-flash) - Score: not computed
- [MAI-Transcribe-2](/models/mai-transcribe-2) - Score: not computed
- [VibeVoice-ASR-Streaming 1.5B](/models/vibevoice-asr-streaming-1-5b) - Score: not computed
- [VibeVoice-ASR-Streaming 7B](/models/vibevoice-asr-streaming-7b) - Score: not computed
- [MAI-Cyber-1-Flash](/models/mai-cyber-1-flash) - Score: not computed
- [MAI-Voice-2-Flash](/models/mai-voice-2-flash) - Score: not computed
- [MAI-Transcribe-1.5](/models/mai-transcribe-1-5) - Score: not computed
- [MAI-Voice-2](/models/mai-voice-2) - Score: not computed
- [Phi-4 Multimodal Instruct](/models/phi-4-multimodal-instruct) - Score: not computed
