# GLM-4.6 vs GLM-4.7

> Side-by-side benchmark comparison for GLM-4.6 and GLM-4.7 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/glm-4-6-vs-glm-4-7
- Last updated: September 4, 2026

- Shared sourced benchmarks: 2
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Evidence is too thin for a benchmark verdict: GLM-4.6 and GLM-4.7 share only 2 sourced benchmark rows.

## Summary

- Only 2 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.

## Model Snapshot

| Property | GLM-4.6 | GLM-4.7 |
|----------|----------|----------|
| Creator | Z.AI | Z.AI |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 200K | 200K |
| Independent public score (not head-to-head) | 53.94 | 58.99 |
| Benchmarks Covered | 3 | 13 |
| Pricing (input/output) | N/A | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- GLM-4.6 public-lane score: Coming soon
- GLM-4.7 public-lane score: 51.1 (Estimated · #57/151)

| Benchmark | GLM-4.6 | GLM-4.7 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | Coming soon | 41% | Coming soon |
| BrowseComp | Coming soon | 52% | Coming soon |
| VITA-Bench | Coming soon | 15.5% | Coming soon |
| Gert Labs | Coming soon | 39.95% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- GLM-4.6 public-lane score: 48.8 (Estimated · #84/183)
- GLM-4.7 public-lane score: 48 (Supported · #86/183)

| Benchmark | GLM-4.6 | GLM-4.7 | Winner |
|-----------|-----------|-----------|--------|
| Vibe Code Bench | 3.09% | Coming soon | Coming soon |
| SWE-bench Verified | Coming soon | 73.8% | Coming soon |
| LiveCodeBench | Coming soon | 84.9% | Coming soon |
| SWE-Rebench | Coming soon | 58.7% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- GLM-4.6 public-lane score: 41.4 (Unranked · 2 rankable rows)
- GLM-4.7 public-lane score: 69.9 (Unranked · 2 rankable rows)

### Knowledge

- Winner: Insufficient shared evidence
- GLM-4.6 public-lane score: 45.3 (Estimated · #115/181)
- GLM-4.7 public-lane score: 48.1 (Supported · #102/181)

| Benchmark | GLM-4.6 | GLM-4.7 | Winner |
|-----------|-----------|-----------|--------|
| GPQA | Coming soon | 85.7% | Coming soon |
| MMLU-Pro | Coming soon | 84.3% | Coming soon |
| HLE | Coming soon | 24.8% | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- GLM-4.6 public-lane score: 42.1 (#98/120)
- GLM-4.7 public-lane score: 82.6 (#49/120)

### Mathematics

- Winner: Insufficient shared evidence
- GLM-4.6 public-lane score: 27.5 (Unranked · 2 rankable rows)
- GLM-4.7 public-lane score: 26 (Unranked · 2 rankable rows)

| Benchmark | GLM-4.6 | GLM-4.7 | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | 3.819% | 2.439% | GLM-4.6 |
| FrontierMath v2 (Tier 4) | 2.128% | 0.000% | GLM-4.6 |
| AIME 2025 | Coming soon | 95.7% | Coming soon |

## FAQ

### Is there enough evidence to pick between GLM-4.6 and GLM-4.7?

Not yet. The models share only 2 sourced benchmark rows, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [GLM-4.6 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-glm-4-6)
- [GLM-4.7 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-glm-4-7)
- [GLM-4.6 vs GPT-6 Astra](/compare/glm-4-6-vs-gpt-6-astra)
- [GLM-4.7 vs GPT-6 Astra](/compare/glm-4-7-vs-gpt-6-astra)

## Explore More

- [GLM-4.6 profile](/models/glm-4-6)
- [GLM-4.7 profile](/models/glm-4-7)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)