# GLM-5 vs MAI-Thinking-1

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

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

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

## Quick Verdict

Pick GLM-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

- GLM-5 leads overall 62.16 to 52.27.
- The clearest category separation is in mathematics, where the averages are 56.9 for GLM-5 and 73.4 for MAI-Thinking-1.
- The biggest single benchmark swing is Terminal-Bench 2.0 in Agentic, with scores of 56.2% and 46%.
- MAI-Thinking-1 also has the larger context window at 256K.

## Model Snapshot

| Property | GLM-5 | MAI-Thinking-1 |
|----------|----------|----------|
| Creator | Z.AI | Microsoft |
| Type | Open Weight | Proprietary |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 200K | 256K |
| Overall Score | 62.16 | 52.27 |
| Benchmarks Covered | 36 | 14 |
| Pricing (input/output) | $1.00 / $3.20 | N/A |

## Category Breakdown

### Agentic

- Winner: Coming soon
- GLM-5 public-lane score: 50 (Estimated · #65/151)
- MAI-Thinking-1 public-lane score: 51.7 (Estimated · #53/151)

| Benchmark | GLM-5 | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 56.2% | 46% | GLM-5 |
| Claw-Eval | 57.7% | Coming soon | Coming soon |
| QwenClawBench | 54.1% | Coming soon | Coming soon |
| τ³-bench results | 65.6% | Coming soon | Coming soon |
| DeepPlanning | 14.6% | Coming soon | Coming soon |
| Toolathlon | 38% | Coming soon | Coming soon |
| MCP Atlas | 31.1% | Coming soon | Coming soon |
| MCP-Tasks | 60.8% | Coming soon | Coming soon |
| WideResearch | 69.8% | Coming soon | Coming soon |
| CyberGym | 43.2% | Coming soon | Coming soon |
| Gert Labs | 50.99% | Coming soon | Coming soon |

### Coding

- Winner: Coming soon
- GLM-5 public-lane score: 49.1 (Supported · #80/183)
- MAI-Thinking-1 public-lane score: 51.8 (Estimated · #60/183)

| Benchmark | GLM-5 | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 77.8% | 73.5% | GLM-5 |
| SWE-bench Verified* | 72.8% | Coming soon | Coming soon |
| SWE-bench Pro | 55.1% | 52.8% | GLM-5 |
| SWE Multilingual | 73.3% | Coming soon | Coming soon |
| SWE-Rebench | 62.8% | Coming soon | Coming soon |
| React Native Evals | 74.8% | Coming soon | Coming soon |
| LiveCodeBench v6 | Coming soon | 87.7% | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 46.0% | Coming soon |

### Reasoning

- Winner: Coming soon
- GLM-5 public-lane score: 51.6 (Unranked · 4 rankable rows)
- MAI-Thinking-1 public-lane score: Coming soon

| Benchmark | GLM-5 | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | 60.8% | Coming soon | Coming soon |
| AI-Needle | 63.3% | Coming soon | Coming soon |
| Graphwalks BFS 128K | Coming soon | 90% | Coming soon |

### Knowledge

- Winner: Coming soon
- GLM-5 public-lane score: 54.9 (Estimated · #62/181)
- MAI-Thinking-1 public-lane score: 53.3 (Estimated · #68/181)

| Benchmark | GLM-5 | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 86% | 84.2% | GLM-5 |
| GPQA-D | 86.0% | 84.2% | GLM-5 |
| SuperGPQA | 66.8% | Coming soon | Coming soon |
| MMLU-Pro | 85.7% | 85% | GLM-5 |
| MMLU-Pro (Arcee) | 85.8% | Coming soon | Coming soon |
| HLE | 50.4% | Coming soon | Coming soon |
| SimpleQA | Coming soon | 31% | Coming soon |

### Instruction Following

- Winner: Coming soon
- GLM-5 public-lane score: 88.3 (#31/120)
- MAI-Thinking-1 public-lane score: 94.7 (#1/120)

| Benchmark | GLM-5 | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 92.6% | Coming soon | Coming soon |
| IFBench | Coming soon | 85% | Coming soon |

### Multilingual

- Winner: Coming soon
- GLM-5 public-lane score: 48.7 (#6/12)
- MAI-Thinking-1 public-lane score: Coming soon

| Benchmark | GLM-5 | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | 83.1% | Coming soon | Coming soon |
| NOVA-63 | 55.1% | Coming soon | Coming soon |

### Mathematics

- Winner: Coming soon
- GLM-5 public-lane score: 56.9 (#7/7)
- MAI-Thinking-1 public-lane score: 73.4 (Unranked · 3 rankable rows)

| Benchmark | GLM-5 | MAI-Thinking-1 | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | 95.8% | 94.5% | GLM-5 |
| AIME25 (Arcee) | 93.3% | Coming soon | Coming soon |
| HMMT Feb 2025 | 97.5% | Coming soon | Coming soon |
| HMMT Nov 2025 | 96.9% | Coming soon | Coming soon |
| HMMT Feb 2026 | 86.4% | 84.9% | GLM-5 |
| MMAnswerBench | 82.5% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | 16.434% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 2.100% | Coming soon | Coming soon |
| AIME 2025 | Coming soon | 97% | Coming soon |

## FAQ

### Which is better overall, GLM-5 or MAI-Thinking-1?

GLM-5 is ahead overall on BenchLM right now.

### Where is the biggest gap between GLM-5 and MAI-Thinking-1?

The widest category gap is in mathematics, where the averages are 56.9 for GLM-5 and 73.4 for MAI-Thinking-1.

### How many benchmarks does GLM-5 cover on BenchLM?

GLM-5 currently has 36 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

- [GLM-5 vs GLM-5.3](/compare/glm-5-vs-glm-5-3)
- [MAI-Thinking-1 vs GLM-5.3](/compare/glm-5-3-vs-mai-thinking-1)
- [GLM-5 vs GLM-5.2](/compare/glm-5-vs-glm-5-2)
- [MAI-Thinking-1 vs GLM-5.2](/compare/glm-5-2-vs-mai-thinking-1)

## Explore More

- [GLM-5 profile](/models/glm-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)