# Claude Sonnet 4.5 vs MAI-Thinking-1

> Side-by-side benchmark comparison for Claude Sonnet 4.5 and MAI-Thinking-1 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/claude-sonnet-4-5-vs-mai-thinking-1
- Last updated: September 4, 2026

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

## Quick Verdict

Pick Claude Sonnet 4.5 if you want the stronger benchmark profile. MAI-Thinking-1 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Claude Sonnet 4.5 leads overall 53.74 to 52.27.
- The clearest category separation is in mathematics, where the averages are 34.8 for Claude Sonnet 4.5 and 73.4 for MAI-Thinking-1.
- The biggest single benchmark swing is AIME 2025 in Mathematics, with scores of 87% and 97%.
- MAI-Thinking-1 also has the larger context window at 256K.

## Model Snapshot

| Property | Claude Sonnet 4.5 | MAI-Thinking-1 |
|----------|----------|----------|
| Creator | Anthropic | Microsoft |
| Type | Proprietary | Proprietary |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 200K | 256K |
| Overall Score | 53.74 | 52.27 |
| Benchmarks Covered | 11 | 14 |
| Pricing (input/output) | $3.00 / $15.00 | N/A |

## Category Breakdown

### Agentic

- Winner: Coming soon
- Claude Sonnet 4.5 public-lane score: 44.6 (Estimated · #100/151)
- MAI-Thinking-1 public-lane score: 51.7 (Estimated · #53/151)

| Benchmark | Claude Sonnet 4.5 | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 50% | 46% | Claude Sonnet 4.5 |
| OSWorld-Verified | 61.4% | Coming soon | Coming soon |
| VITA-Bench | 17.0% | Coming soon | Coming soon |
| Gert Labs | 48.51% | Coming soon | Coming soon |
| JobBench | 27.7% | Coming soon | Coming soon |

### Coding

- Winner: Coming soon
- Claude Sonnet 4.5 public-lane score: 51 (Estimated · #67/183)
- MAI-Thinking-1 public-lane score: 51.8 (Estimated · #60/183)

| Benchmark | Claude Sonnet 4.5 | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 77.2% | 73.5% | Claude Sonnet 4.5 |
| 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: Coming soon
- Claude Sonnet 4.5 public-lane score: 19.1 (Unranked · 1 rankable row)
- MAI-Thinking-1 public-lane score: Coming soon

| Benchmark | Claude Sonnet 4.5 | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-2 | 13.6% | Coming soon | Coming soon |
| Graphwalks BFS 128K | Coming soon | 90% | Coming soon |

### Knowledge

- Winner: Coming soon
- Claude Sonnet 4.5 public-lane score: 51.5 (Estimated · #81/181)
- MAI-Thinking-1 public-lane score: 53.3 (Estimated · #68/181)

| Benchmark | Claude Sonnet 4.5 | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 83.4% | 84.2% | MAI-Thinking-1 |
| GPQA-D | Coming soon | 84.2% | Coming soon |
| MMLU-Pro | Coming soon | 85% | Coming soon |
| SimpleQA | Coming soon | 31% | Coming soon |

### Instruction Following

- Winner: Coming soon
- Claude Sonnet 4.5 public-lane score: Coming soon
- MAI-Thinking-1 public-lane score: 94.7 (#1/120)

| Benchmark | Claude Sonnet 4.5 | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| IFBench | Coming soon | 85% | Coming soon |

### Mathematics

- Winner: Coming soon
- Claude Sonnet 4.5 public-lane score: 34.8 (Unranked · 2 rankable rows)
- MAI-Thinking-1 public-lane score: 73.4 (Unranked · 3 rankable rows)

| Benchmark | Claude Sonnet 4.5 | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| AIME 2025 | 87% | 97% | MAI-Thinking-1 |
| FrontierMath v2 (Tiers 1-3) | 13.495% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 4.167% | Coming soon | Coming soon |
| AIME26 | Coming soon | 94.5% | Coming soon |
| HMMT Feb 2026 | Coming soon | 84.9% | Coming soon |

## FAQ

### Which is better overall, Claude Sonnet 4.5 or MAI-Thinking-1?

Claude Sonnet 4.5 is ahead overall on BenchLM right now.

### Where is the biggest gap between Claude Sonnet 4.5 and MAI-Thinking-1?

The widest category gap is in mathematics, where the averages are 34.8 for Claude Sonnet 4.5 and 73.4 for MAI-Thinking-1.

### How many benchmarks does Claude Sonnet 4.5 cover on BenchLM?

Claude Sonnet 4.5 currently has 11 sourced benchmark scores on BenchLM.

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

MAI-Thinking-1 currently has 14 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Claude Sonnet 4.5 vs Claude Sonnet 4.5 Thinking](/compare/claude-sonnet-4-5-vs-claude-sonnet-4-5-thinking)
- [MAI-Thinking-1 vs Claude Sonnet 4.5 Thinking](/compare/claude-sonnet-4-5-thinking-vs-mai-thinking-1)
- [Claude Sonnet 4.5 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-claude-sonnet-4-5)
- [MAI-Thinking-1 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-mai-thinking-1)

## Explore More

- [Claude Sonnet 4.5 profile](/models/claude-sonnet-4-5)
- [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)