# GLM-5.1 vs Hy4 preview

> Side-by-side benchmark comparison for GLM-5.1 and Hy4 preview across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/glm-5-1-vs-hy4-preview
- Last updated: October 13, 2026

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

## Quick Verdict

Hy4 preview leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Hy4 preview has the higher overall point estimate 60.86 to 56.05. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in agentic, where the averages are 42.5 for GLM-5.1 and 54.5 for Hy4 preview.
- The biggest single benchmark swing is HLE in Knowledge, with scores of 31% and 55.4%.
- Hy4 preview is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Hy4 preview also has the larger context window at 1M.

## Model Snapshot

| Property | GLM-5.1 | Hy4 preview |
|----------|----------|----------|
| Creator | Z.AI | Tencent |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 203K | 1M |
| Overall Score | 56.05 | 60.86 |
| Benchmarks Covered | 27 | 30 |
| Pricing (input/output) | $1.40 / $4.40 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Directional only
- GLM-5.1 public-lane score: 42.5 (Estimated · #59/123)
- Hy4 preview public-lane score: 54.5 (Estimated · #37/123)

| Benchmark | GLM-5.1 | Hy4 preview | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 63.5% | Coming soon | Coming soon |
| BrowseComp | 68% | Coming soon | Coming soon |
| τ³-bench results | 70.6% | Coming soon | Coming soon |
| MCP Atlas | 71.8% | 83.7% | Hy4 preview |
| CyberGym | 68.7% | 78.4% | Hy4 preview |
| Claw-Eval | 62.3% | Coming soon | Coming soon |
| Gert Labs | 60.11% | Coming soon | Coming soon |
| ResearchClawBench | 18.2% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 56.9% | 55.1% | GLM-5.1 |
| HLE w/ tools | 52.3% | 55.4% | Hy4 preview |
| Terminal-Bench 2.1 | Coming soon | 85.4% | Coming soon |
| WideResearch | Coming soon | 83.9% | Coming soon |
| DRACO | Coming soon | 77.2% | Coming soon |
| Toolathlon-Verified | Coming soon | 74.1% | Coming soon |
| APEX-Agents | Coming soon | 37.1% | Coming soon |
| skillsBench | Coming soon | 62.9% | Coming soon |
| JobBench | Coming soon | 61.7% | Coming soon |
| Agents' Last Exam | Coming soon | 22.8% | Coming soon |
| AutomationBench | Coming soon | 32.1% | Coming soon |
| BankerToolBench | Coming soon | 78.6% | Coming soon |
| CWE-bench v1 | Coming soon | 53.0% | Coming soon |

### Coding

- Winner: Hy4 preview
- GLM-5.1 public-lane score: 47.6 (Supported · #48/148)
- Hy4 preview public-lane score: 57.1 (Supported · #26/148)

| Benchmark | GLM-5.1 | Hy4 preview | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Pro | 58.4% | 65.7% | Hy4 preview |
| NL2Repo | 42.7% | 58.9% | Hy4 preview |
| SWE-Rebench | 62.7% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | 63.5% | Coming soon | Coming soon |
| Vibe Code Bench | 31.46% | Coming soon | Coming soon |
| OpenHarmony Bench | 52.3% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 81.4% | Coming soon | Coming soon |
| SWE-bench (Vals) | 76.4% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 85.4% | Coming soon |
| SWE Multilingual | Coming soon | 82.9% | Coming soon |
| DeepSWE | Coming soon | 64.3% | Coming soon |
| ProgramBench | Coming soon | 17.5% | Coming soon |
| PostTrain Bench | Coming soon | 35.6% | Coming soon |
| sweMarathon | Coming soon | 31.9% | Coming soon |

### Reasoning

- Winner: Not comparable
- GLM-5.1 public-lane score: 76.5 (Unranked · 2 rankable rows)
- Hy4 preview public-lane score: Coming soon

| Benchmark | GLM-5.1 | Hy4 preview | Winner |
|-----------|-----------|-----------|--------|
| CritPt | Coming soon | 16.9% | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- GLM-5.1 public-lane score: Coming soon
- Hy4 preview public-lane score: 88.3 (Unranked · 1 rankable row)

| Benchmark | GLM-5.1 | Hy4 preview | Winner |
|-----------|-----------|-----------|--------|
| OfficeQA Pro | Coming soon | 66.2% | Coming soon |

### Knowledge

- Winner: Directional only
- GLM-5.1 public-lane score: 52.3 (Supported · #69/180)
- Hy4 preview public-lane score: 63.6 (Estimated · #39/180)

| Benchmark | GLM-5.1 | Hy4 preview | Winner |
|-----------|-----------|-----------|--------|
| GPQA-D | 86.2% | 92.3% | Hy4 preview |
| HLE | 31% | 55.4% | Hy4 preview |
| GPQA Diamond (Vals) | 84.5% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 86.9% | Coming soon | Coming soon |
| GPQA | Coming soon | 92.3% | Coming soon |
| HLE w/o tools | Coming soon | 43.4% | Coming soon |

### Instruction Following

- Winner: Not comparable
- GLM-5.1 public-lane score: 93.8 (#6/127)
- Hy4 preview public-lane score: Coming soon

### Mathematics

- Winner: Not comparable
- GLM-5.1 public-lane score: 66.7 (#7/12)
- Hy4 preview public-lane score: Coming soon

| Benchmark | GLM-5.1 | Hy4 preview | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | 95.3% | Coming soon | Coming soon |
| HMMT Nov 2025 | 94.0% | Coming soon | Coming soon |
| HMMT Feb 2026 | 82.6% | Coming soon | Coming soon |
| MMAnswerBench | 83.8% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | 36.842% | Coming soon | Coming soon |
| Apex | Coming soon | 74.2% | Coming soon |

## FAQ

### Which is better overall, GLM-5.1 or Hy4 preview?

Hy4 preview has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between GLM-5.1 and Hy4 preview?

The widest category gap is in agentic, where the averages are 42.5 for GLM-5.1 and 54.5 for Hy4 preview.

### How many benchmarks does GLM-5.1 cover on BenchLM?

GLM-5.1 currently has 27 sourced benchmark scores on BenchLM.

### How many benchmarks does Hy4 preview cover on BenchLM?

Hy4 preview currently has 30 sourced benchmark scores on BenchLM.

## Related Comparisons

- [GLM-5.1 vs GLM-5.3](/compare/glm-5-1-vs-glm-5-3)
- [Hy4 preview vs GLM-5.3](/compare/glm-5-3-vs-hy4-preview)
- [GLM-5.1 vs GLM-5.2](/compare/glm-5-1-vs-glm-5-2)
- [Hy4 preview vs GLM-5.2](/compare/glm-5-2-vs-hy4-preview)

## Explore More

- [GLM-5.1 profile](/models/glm-5-1)
- [Hy4 preview profile](/models/hy4-preview)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)