# Kimi K2.5 (Reasoning) vs MAI-Thinking-1

> Side-by-side benchmark comparison for Kimi K2.5 (Reasoning) and MAI-Thinking-1 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/kimi-k2-5-reasoning-vs-mai-thinking-1
- Last updated: September 4, 2026

- Shared sourced benchmarks: 5
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick Kimi K2.5 (Reasoning) 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

- Kimi K2.5 (Reasoning) leads overall 58.74 to 52.27.
- The clearest category separation is in agentic, where the averages are 49.9 for Kimi K2.5 (Reasoning) and 51.7 for MAI-Thinking-1.
- The biggest single benchmark swing is Terminal-Bench 2.0 in Agentic, with scores of 50.8% and 46%.
- MAI-Thinking-1 also has the larger context window at 256K.

## Model Snapshot

| Property | Kimi K2.5 (Reasoning) | MAI-Thinking-1 |
|----------|----------|----------|
| Creator | Moonshot AI | Microsoft |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 128K | 256K |
| Overall Score | 58.74 | 52.27 |
| Benchmarks Covered | 9 | 14 |
| Pricing (input/output) | $0.60 / $3.00 | N/A |

## Category Breakdown

### Agentic

- Winner: Coming soon
- Kimi K2.5 (Reasoning) public-lane score: 49.9 (Estimated · #67/151)
- MAI-Thinking-1 public-lane score: 51.7 (Estimated · #53/151)

| Benchmark | Kimi K2.5 (Reasoning) | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 50.8% | 46% | Kimi K2.5 (Reasoning) |
| BrowseComp | 60.6% | Coming soon | Coming soon |
| Gert Labs | 32.58% | Coming soon | Coming soon |

### Coding

- Winner: Coming soon
- Kimi K2.5 (Reasoning) public-lane score: 52.9 (Estimated · #52/183)
- MAI-Thinking-1 public-lane score: 51.8 (Estimated · #60/183)

| Benchmark | Kimi K2.5 (Reasoning) | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 76.8% | 73.5% | Kimi K2.5 (Reasoning) |
| Vibe Code Bench | 17.54% | Coming soon | Coming soon |
| 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 |

### Multimodal & Grounded

- Winner: Coming soon
- Kimi K2.5 (Reasoning) public-lane score: 63.2 (Unranked · 1 rankable row)
- MAI-Thinking-1 public-lane score: Coming soon

| Benchmark | Kimi K2.5 (Reasoning) | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 78.5% | Coming soon | Coming soon |

### Reasoning

- Winner: Coming soon
- Kimi K2.5 (Reasoning) public-lane score: Coming soon
- MAI-Thinking-1 public-lane score: Coming soon

| Benchmark | Kimi K2.5 (Reasoning) | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| Graphwalks BFS 128K | Coming soon | 90% | Coming soon |

### Knowledge

- Winner: Coming soon
- Kimi K2.5 (Reasoning) public-lane score: 52.4 (Estimated · #78/181)
- MAI-Thinking-1 public-lane score: 53.3 (Estimated · #68/181)

| Benchmark | Kimi K2.5 (Reasoning) | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 87.6% | 84.2% | Kimi K2.5 (Reasoning) |
| MMLU-Pro | 87.1% | 85% | Kimi K2.5 (Reasoning) |
| GPQA-D | Coming soon | 84.2% | Coming soon |
| SimpleQA | Coming soon | 31% | Coming soon |

### Instruction Following

- Winner: Coming soon
- Kimi K2.5 (Reasoning) public-lane score: Coming soon
- MAI-Thinking-1 public-lane score: 94.7 (#1/120)

| Benchmark | Kimi K2.5 (Reasoning) | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| IFBench | Coming soon | 85% | Coming soon |

### Mathematics

- Winner: Coming soon
- Kimi K2.5 (Reasoning) public-lane score: Coming soon
- MAI-Thinking-1 public-lane score: 73.4 (Unranked · 3 rankable rows)

| Benchmark | Kimi K2.5 (Reasoning) | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| AIME 2025 | 96.1% | 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, Kimi K2.5 (Reasoning) or MAI-Thinking-1?

Kimi K2.5 (Reasoning) is ahead overall on BenchLM right now.

### Where is the biggest gap between Kimi K2.5 (Reasoning) and MAI-Thinking-1?

The widest category gap is in agentic, where the averages are 49.9 for Kimi K2.5 (Reasoning) and 51.7 for MAI-Thinking-1.

### How many benchmarks does Kimi K2.5 (Reasoning) cover on BenchLM?

Kimi K2.5 (Reasoning) currently has 9 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

- [Kimi K2.5 (Reasoning) vs Kimi K2.5](/compare/kimi-k2-5-vs-kimi-k2-5-reasoning)
- [MAI-Thinking-1 vs Kimi K2.5](/compare/kimi-k2-5-vs-mai-thinking-1)
- [Kimi K2.5 (Reasoning) vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-kimi-k2-5-reasoning)
- [MAI-Thinking-1 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-mai-thinking-1)

## Explore More

- [Kimi K2.5 (Reasoning) profile](/models/kimi-k2-5-reasoning)
- [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)