# GLM-4.6 vs GLM-4.7

> GLM-4.6 and GLM-4.7 score almost the same on the Noometry Index (40.9 vs 41.7), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/glm-4-6-vs-glm-4-7
- Last updated: 2026-10-10
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. GLM-4.6 scores higher in 4 categories and GLM-4.7 in 5 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.7 leads 47.0 to 39.6.
- The biggest single-benchmark swing is Terminal-Bench: 24.5% for GLM-4.6 and 33.4% for GLM-4.7.
- Both cost about the same: $0.60 input and $2.20 output per million tokens.

## Snapshot

| | GLM-4.6 | GLM-4.7 |
|---|---|---|
| Provider | Z.ai (Zhipu) | Z.ai (Zhipu) |
| Noometry Index | 40.9 | 41.7 |
| Rank | 132 | 117 |
| Context | 205K | 205K |
| Input $/M | $0.60 | $0.60 |
| Output $/M | $2.20 | $2.20 |
| Weights | Open | Open |

## Coding

- GLM-4.6: 39.9 (#137)
- GLM-4.7: 43.6 (#74)

| Benchmark | GLM-4.6 | GLM-4.7 |
|---|---|---|
| LMArena WebDev | 1339 | 1435 |
| SciCode | 38.4% | 45.1% |
| LMArena Coding | 1449 | 1454 |
| ALE-Bench | 340.82 | 399.48 |
| SWE-bench Verified (bash only) | 55.4% | — |

## Agentic & Tool Use

- GLM-4.6: 32.1 (#60)
- GLM-4.7: 26.4 (#96)

| Benchmark | GLM-4.6 | GLM-4.7 |
|---|---|---|
| Terminal-Bench | 24.5% | 33.4% |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| Vending-Bench 2 | — | 2,377 |

## Reasoning

- GLM-4.6: 23.1 (#168)
- GLM-4.7: 23.7 (#161)

| Benchmark | GLM-4.6 | GLM-4.7 |
|---|---|---|
| CritPt | 1.1% | 1.7% |
| LMArena Hard Prompts | 1440 | 1443 |
| SimpleBench | — | 47.7% |
| Kagi LLM Benchmark | 47.4% | — |
| Chess Puzzles | — | 6% |
| Epoch Capabilities Index | — | 143.53 |

## Math

- GLM-4.6: 36.4 (#115)
- GLM-4.7: 37.7 (#92)

| Benchmark | GLM-4.6 | GLM-4.7 |
|---|---|---|
| LMArena Math | 1431 | 1423 |
| FrontierMath (Feb 2025 set) | 3.8% | 2.4% |
| FrontierMath Tier 4 (v1) | 2.1% | 0% |
| OTIS Mock AIME 2024-2025 | — | 83.3% |
| ProofBench | — | 6% |

## Knowledge

- GLM-4.6: 39.6 (#118)
- GLM-4.7: 47.0 (#74)

| Benchmark | GLM-4.6 | GLM-4.7 |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 11.7% |
| LMArena Expert | 1432 | 1424 |
| GPQA Diamond | — | 83.3% |
| SimpleQA Verified | — | 32.2% |

## Multilingual

- GLM-4.6: 53.6 (#62)
- GLM-4.7: 53.0 (#75)

| Benchmark | GLM-4.6 | GLM-4.7 |
|---|---|---|
| LMArena Non-English | 1426 | 1417 |
| LMArena Chinese | 1500 | 1495 |
| LMArena French | 1459 | 1432 |
| LMArena German | 1447 | 1426 |
| LMArena Japanese | 1394 | 1439 |
| LMArena Korean | 1401 | 1401 |
| LMArena Russian | 1418 | 1423 |
| LMArena Spanish | 1436 | 1433 |

## Instruction Following

- GLM-4.6: 74.5 (#93)
- GLM-4.7: 74.6 (#90)

| Benchmark | GLM-4.6 | GLM-4.7 |
|---|---|---|
| LMArena Instruction Following | 1410 | 1411 |

## Long Context

- GLM-4.6: 43.4 (#91)
- GLM-4.7: 42.8 (#111)

| Benchmark | GLM-4.6 | GLM-4.7 |
|---|---|---|
| LMArena Longer Query | 1423 | 1432 |
| CL-bench | — | 15.9% |
| CL-bench Life | — | 10.9% |

## Writing & Preference

- GLM-4.6: 61.3 (#86)
- GLM-4.7: 61.1 (#89)

| Benchmark | GLM-4.6 | GLM-4.7 |
|---|---|---|
| LMArena Text | 1440 | 1436 |
| LMArena Creative Writing | 1411 | 1401 |
| EQ-Bench Creative Writing | 1411 | 1413 |
| LMArena Multi-Turn | 1427 | 1446 |

## FAQ

### Is GLM-4.6 better than GLM-4.7?

GLM-4.6 and GLM-4.7 score almost the same on the Noometry Index (40.9 vs 41.7), so choose on price, context window or the category you care about most.

### Which is cheaper, GLM-4.6 or GLM-4.7?

GLM-4.7 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.

### Is GLM-4.6 or GLM-4.7 better for coding?

GLM-4.7 scores higher on coding benchmarks: 43.6 versus 39.9 in the Noometry coding category.

### Which has the bigger context window?

Both accept 205K tokens.

### How many benchmarks do GLM-4.6 and GLM-4.7 share?

26 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and GLM-4.7 has 36.