# MAI-Thinking-1 Benchmark Scores & Performance

> MAI-Thinking-1 by Microsoft scores 52.27/100 overall, ranking #116 out of 411 AI models.

Canonical page: https://benchlm.ai/models/mai-thinking-1

Last updated: September 4, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Microsoft |
| Source Type | Proprietary |
| Reasoning Type | Reasoning |
| Context Window | 256K |
| Overall Score | 52.27/100 |
| Overall Rank | #116 of 411 |

## Family & Coverage

- Family: MAI-Thinking
- Variant: 1
- Benchmarks covered: 14 of 422
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score |
|-----------|-------|
| [Terminal-Bench 2.0](/benchmarks/terminal-bench-2) | 46% |

## Coding Benchmarks

| Benchmark | Score |
|-----------|-------|
| [LiveCodeBench v6](/benchmarks/livecodebench-v6) | 87.7% |
| [SWE-bench Verified](/benchmarks/swe-bench-verified) | 73.5% |
| [SWE-bench Pro](/benchmarks/swe-bench-pro) | 52.8% |
| [Terminal-Bench 2.0](/benchmarks/terminal-bench-2) | 46.0% |

## Reasoning Benchmarks

| Benchmark | Score |
|-----------|-------|
| [Graphwalks BFS 128K](/benchmarks/graphwalksbfs128k) | 90% |

## Knowledge Benchmarks

| Benchmark | Score |
|-----------|-------|
| [GPQA](/benchmarks/gpqa) | 84.2% |
| [GPQA-D](/benchmarks/gpqa-diamond) | 84.2% |
| [MMLU-Pro](/benchmarks/mmlu-pro) | 85% |
| [SimpleQA](/benchmarks/simpleqa) | 31% |

## Instruction Following Benchmarks

| Benchmark | Score |
|-----------|-------|
| [IFBench](/benchmarks/ifbench) | 85% |

## Mathematics Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AIME 2025](/benchmarks/aime2025) | 97% |
| [AIME26](/benchmarks/aime2026) | 94.5% |
| [HMMT Feb 2026](/benchmarks/hmmtfeb2026) | 84.9% |

## Other Microsoft Models

- [Phi-4](/models/phi-4) - Score: 32.91
- [MAI-Voice-2](/models/mai-voice-2) - Score: not computed
- [Phi-4 Multimodal Instruct](/models/phi-4-multimodal-instruct) - Score: not computed