# DeepSeek-R1-0528 vs MAI-Thinking-1

> Side-by-side benchmark comparison for DeepSeek-R1-0528 and MAI-Thinking-1 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/deepseek-r1-0528-vs-mai-thinking-1
- Last updated: October 14, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

DeepSeek-R1-0528 leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- DeepSeek-R1-0528 has the higher overall point estimate 60 to 53.43. Conditional score ranges do not establish rank confidence.
- The biggest single benchmark swing is SWE-bench Verified in Coding, with scores of 57.6% and 73.5%.
- MAI-Thinking-1 also has the larger context window at 256K.

## Model Snapshot

| Property | DeepSeek-R1-0528 | MAI-Thinking-1 |
|----------|----------|----------|
| Creator | DeepSeek | Microsoft |
| Type | Open Weight | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 128K | 256K |
| Overall Score | null | 53.43 |
| Benchmarks Covered | 10 | 13 |
| Pricing (input/output) | N/A | N/A |

## Category Breakdown

### Agentic

- Winner: Not comparable
- DeepSeek-R1-0528 public-lane score: Coming soon
- MAI-Thinking-1 public-lane score: Coming soon

| Benchmark | DeepSeek-R1-0528 | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | Coming soon | 46% | Coming soon |

### Coding

- Winner: Not comparable
- DeepSeek-R1-0528 public-lane score: Coming soon
- MAI-Thinking-1 public-lane score: Coming soon

| Benchmark | DeepSeek-R1-0528 | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench | 73.3% | Coming soon | Coming soon |
| Codeforces | 1930.0 | Coming soon | Coming soon |
| SWE-bench Verified | 57.6% | 73.5% | MAI-Thinking-1 |
| LiveCodeBench v6 | Coming soon | 87.7% | Coming soon |
| SWE-bench Pro | Coming soon | 52.8% | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 46.0% | Coming soon |

### Reasoning

- Winner: Not comparable
- DeepSeek-R1-0528 public-lane score: Coming soon
- MAI-Thinking-1 public-lane score: Coming soon

| Benchmark | DeepSeek-R1-0528 | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| Graphwalks BFS 128K | Coming soon | 90% | Coming soon |

### Knowledge

- Winner: Not comparable
- DeepSeek-R1-0528 public-lane score: Coming soon
- MAI-Thinking-1 public-lane score: 55.6 (Estimated · #55/181)

| Benchmark | DeepSeek-R1-0528 | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| MMLU-Redux | 93.4% | Coming soon | Coming soon |
| MMLU-Pro | 85% | 85% | Tie |
| GPQA | 81% | 84.2% | MAI-Thinking-1 |
| SimpleQA | 27.8% | Coming soon | Coming soon |
| HLE | 17.7% | Coming soon | Coming soon |
| GPQA-D | Coming soon | 84.2% | Coming soon |

### Instruction Following

- Winner: Not comparable
- DeepSeek-R1-0528 public-lane score: Coming soon
- MAI-Thinking-1 public-lane score: 94.7 (#3/128)

| Benchmark | DeepSeek-R1-0528 | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| IFBench | Coming soon | 85% | Coming soon |

### Mathematics

- Winner: Not comparable
- DeepSeek-R1-0528 public-lane score: Coming soon
- MAI-Thinking-1 public-lane score: 81.1 (Unranked · 3 rankable rows)

| Benchmark | DeepSeek-R1-0528 | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| AIME 2024 | 91.4% | Coming soon | Coming soon |
| AIME 2025 | 87.5% | 97% | MAI-Thinking-1 |
| AIME26 | Coming soon | 94.5% | Coming soon |
| HMMT Feb 2026 | Coming soon | 84.9% | Coming soon |

## FAQ

### Which is better overall, DeepSeek-R1-0528 or MAI-Thinking-1?

DeepSeek-R1-0528 has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### How many benchmarks does DeepSeek-R1-0528 cover on BenchLM?

DeepSeek-R1-0528 currently has 10 sourced benchmark scores on BenchLM.

### How many benchmarks does MAI-Thinking-1 cover on BenchLM?

MAI-Thinking-1 currently has 13 sourced benchmark scores on BenchLM.

## Related Comparisons

- [DeepSeek-R1-0528 vs DeepSeek-R1](/compare/deepseek-r1-vs-deepseek-r1-0528)
- [MAI-Thinking-1 vs DeepSeek-R1](/compare/deepseek-r1-vs-mai-thinking-1)
- [DeepSeek-R1-0528 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-deepseek-r1-0528)
- [MAI-Thinking-1 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-mai-thinking-1)

## Explore More

- [DeepSeek-R1-0528 profile](/models/deepseek-r1-0528)
- [MAI-Thinking-1 profile](/models/mai-thinking-1)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)