# GLM-5.1 vs GLM-5.2

> Side-by-side benchmark comparison for GLM-5.1 and GLM-5.2 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/glm-5-1-vs-glm-5-2
- Last updated: September 14, 2026

- Shared sourced benchmarks: 17
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick GLM-5.2 if you want the stronger benchmark profile. GLM-5.1 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- GLM-5.2 leads overall 68.19 to 63.3.
- The clearest category separation is in mathematics, where the averages are 64.1 for GLM-5.1 and 80.7 for GLM-5.2.
- The biggest single benchmark swing is Terminal-Bench 2.0 in Agentic, with scores of 63.5% and 81%.
- GLM-5.2 also has the larger context window at 1M.

## Model Snapshot

| Property | GLM-5.1 | GLM-5.2 |
|----------|----------|----------|
| Creator | Z.AI | Z.AI |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 203K | 1M |
| Overall Score | 63.3 | 68.19 |
| Benchmarks Covered | 26 | 25 |
| Pricing (input/output) | $1.40 / $4.40 | $1.40 / $4.40 |

## Category Breakdown

### Agentic

- Winner: Coming soon
- GLM-5.1 public-lane score: 54.3 (Estimated · #38/153)
- GLM-5.2 public-lane score: 58.5 (Supported · #29/153)

| Benchmark | GLM-5.1 | GLM-5.2 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 63.5% | 81% | GLM-5.2 |
| BrowseComp | 68% | Coming soon | Coming soon |
| τ³-bench results | 70.6% | Coming soon | Coming soon |
| MCP Atlas | 71.8% | 76.8% | GLM-5.2 |
| CyberGym | 68.7% | Coming soon | Coming soon |
| Claw-Eval | 62.3% | Coming soon | Coming soon |
| Gert Labs | 60.11% | Coming soon | Coming soon |
| ResearchClawBench | 18.2% | 20.7% | GLM-5.2 |
| Terminal-Bench 2.1 (Vals) | 56.9% | 67.8% | GLM-5.2 |
| Terminal-Bench 3.0 | Coming soon | 4.6% | Coming soon |
| Toolathlon | Coming soon | 48.2% | Coming soon |

### Coding

- Winner: GLM-5.2
- GLM-5.1 public-lane score: 56.5 (Supported · #38/152)
- GLM-5.2 public-lane score: 61 (Supported · #19/152)

| Benchmark | GLM-5.1 | GLM-5.2 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Pro | 58.4% | 62.1% | GLM-5.2 |
| NL2Repo | 42.7% | 48.9% | GLM-5.2 |
| SWE-Rebench | 62.7% | Coming soon | Coming soon |
| Vibe Code Bench | 31.46% | Coming soon | Coming soon |
| OpenHarmony Bench | 52.3% | 58.4% | GLM-5.2 |
| LiveCodeBench (Vals) | 81.4% | 69.5% | GLM-5.1 |
| SWE-bench (Vals) | 76.4% | 82.8% | GLM-5.2 |
| Terminal-Bench 2.0 | Coming soon | 81.0% | Coming soon |
| ProgramBench | Coming soon | 63.7% | Coming soon |
| cursorBench32 | Coming soon | 55.0% | Coming soon |

### Reasoning

- Winner: Coming soon
- GLM-5.1 public-lane score: 71.7 (Unranked · 2 rankable rows)
- GLM-5.2 public-lane score: 74.8 (Unranked · 2 rankable rows)

| Benchmark | GLM-5.1 | GLM-5.2 | Winner |
|-----------|-----------|-----------|--------|
| CritPt | Coming soon | 20.9% | Coming soon |

### Knowledge

- Winner: GLM-5.2
- GLM-5.1 public-lane score: 54.8 (Supported · #54/183)
- GLM-5.2 public-lane score: 60.7 (Supported · #35/183)

| Benchmark | GLM-5.1 | GLM-5.2 | Winner |
|-----------|-----------|-----------|--------|
| GPQA-D | 86.2% | 91.2% | GLM-5.2 |
| HLE | 52.3% | 54.7% | GLM-5.2 |
| GPQA Diamond (Vals) | 84.5% | 85.6% | GLM-5.2 |
| MMLU-Pro (Vals) | 86.9% | 86.7% | GLM-5.1 |
| GPQA | Coming soon | 91.2% | Coming soon |
| HLE w/o tools | Coming soon | 40.5% | Coming soon |

### Instruction Following

- Winner: Coming soon
- GLM-5.1 public-lane score: 93.7 (#5/123)
- GLM-5.2 public-lane score: 89.8 (#22/123)

### Mathematics

- Winner: Coming soon
- GLM-5.1 public-lane score: 64.1 (#3/7)
- GLM-5.2 public-lane score: 80.7 (Unranked · 4 rankable rows)

| Benchmark | GLM-5.1 | GLM-5.2 | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | 95.3% | 99.2% | GLM-5.2 |
| HMMT Nov 2025 | 94.0% | 94.4% | GLM-5.2 |
| HMMT Feb 2026 | 82.6% | 92.5% | GLM-5.2 |
| MMAnswerBench | 83.8% | 91.0% | GLM-5.2 |
| FrontierMath v2 (Tiers 1-3) | 33.448% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 12.500% | Coming soon | Coming soon |

## FAQ

### Which is better overall, GLM-5.1 or GLM-5.2?

GLM-5.2 is ahead overall on BenchLM right now.

### Where is the biggest gap between GLM-5.1 and GLM-5.2?

The widest category gap is in mathematics, where the averages are 64.1 for GLM-5.1 and 80.7 for GLM-5.2.

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

GLM-5.1 currently has 26 sourced benchmark scores on BenchLM.

### How many benchmarks does GLM-5.2 cover on BenchLM?

GLM-5.2 currently has 25 sourced benchmark scores on BenchLM.

## Related Comparisons

- [GLM-5.1 vs GLM-5.3](/compare/glm-5-1-vs-glm-5-3)
- [GLM-5.2 vs GLM-5.3](/compare/glm-5-2-vs-glm-5-3)
- [GLM-5.1 vs GLM-5.3-Flash](/compare/glm-5-1-vs-glm-5-3-flash)
- [GLM-5.2 vs GLM-5.3-Flash](/compare/glm-5-2-vs-glm-5-3-flash)

## Explore More

- [GLM-5.1 profile](/models/glm-5-1)
- [GLM-5.2 profile](/models/glm-5-2)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)