# Claude Sonnet 5.5 vs GLM-4.7

> Claude Sonnet 5.5 is the stronger model overall, scoring 60.5 to 41.7 on the Noometry Index. GLM-4.7 costs 4.0× less per token, which makes it the better buy when Claude Sonnet 5.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-sonnet-5-5-vs-glm-4-7
- Last updated: 2026-10-10
- Shared benchmarks: 8

## Summary

- They share 8 benchmarks with published results for both. Claude Sonnet 5.5 scores higher in 5 categories and GLM-4.7 in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5.5 leads 88.7 to 37.7.
- The biggest single-benchmark swing is ProofBench: 100% for Claude Sonnet 5.5 and 6% for GLM-4.7.
- GLM-4.7 is cheaper at $0.60 / $2.20 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.5.
- Claude Sonnet 5.5 accepts more context: 1M tokens versus 205K.
- GLM-4.7 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 5.5 | GLM-4.7 |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 60.5 | 41.7 |
| Rank | 10 | 117 |
| Context | 1M | 205K |
| Input $/M | $2 | $0.60 |
| Output $/M | $10 | $2.20 |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 5.5: 65.5 (#6)
- GLM-4.7: 43.6 (#74)

| Benchmark | Claude Sonnet 5.5 | GLM-4.7 |
|---|---|---|
| LMArena WebDev | 1699 | 1435 |
| SciCode | 61% | 45.1% |
| ALE-Bench | 1,819 | 399.48 |
| FrontierCode | 52.1% | — |
| CursorBench | 55.5% | — |
| FrontierSWE | 61.9% | — |
| LMArena Coding | — | 1454 |

## Agentic & Tool Use

- Claude Sonnet 5.5: 44.9 (#14)
- GLM-4.7: 26.4 (#96)

| Benchmark | Claude Sonnet 5.5 | GLM-4.7 |
|---|---|---|
| Terminal-Bench | — | 33.4% |
| APEX-Agents | 75.5% | — |
| Vending-Bench 2 | — | 2,377 |

## Reasoning

- Claude Sonnet 5.5: 52.4 (#29)
- GLM-4.7: 23.7 (#161)

| Benchmark | Claude Sonnet 5.5 | GLM-4.7 |
|---|---|---|
| CritPt | 31.4% | 1.7% |
| SimpleBench | — | 47.7% |
| Chess Puzzles | — | 6% |
| LMArena Hard Prompts | — | 1443 |
| Mystery Game Puzzles | 65% | — |
| Epoch Capabilities Index | — | 143.53 |

## Math

- Claude Sonnet 5.5: 88.7 (#4)
- GLM-4.7: 37.7 (#92)

| Benchmark | Claude Sonnet 5.5 | GLM-4.7 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 83.3% |
| ProofBench | 100% | 6% |
| FrontierMath (Tiers 1-3) | 88.8% | — |
| FrontierMath Tier 4 | 80.5% | — |
| LMArena Math | — | 1423 |
| FrontierMath (Feb 2025 set) | — | 2.4% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Claude Sonnet 5.5: 66.0 (#11)
- GLM-4.7: 47.0 (#74)

| Benchmark | Claude Sonnet 5.5 | GLM-4.7 |
|---|---|---|
| GPQA Diamond | 95.6% | 83.3% |
| SimpleQA Verified | 46.5% | 32.2% |
| Vectara Hallucination Rate | — | 11.7% |
| LMArena Expert | — | 1424 |

## Multimodal

- Claude Sonnet 5.5: 53.2 (#5)
- GLM-4.7: —

| Benchmark | Claude Sonnet 5.5 | GLM-4.7 |
|---|---|---|
| Furniture Assembly | 75% | — |

## Multilingual

- Claude Sonnet 5.5: —
- GLM-4.7: 53.0 (#75)

| Benchmark | Claude Sonnet 5.5 | GLM-4.7 |
|---|---|---|
| LMArena Non-English | — | 1417 |
| LMArena Chinese | — | 1495 |
| LMArena French | — | 1432 |
| LMArena German | — | 1426 |
| LMArena Japanese | — | 1439 |
| LMArena Korean | — | 1401 |
| LMArena Russian | — | 1423 |
| LMArena Spanish | — | 1433 |

## Instruction Following

- Claude Sonnet 5.5: —
- GLM-4.7: 74.6 (#90)

| Benchmark | Claude Sonnet 5.5 | GLM-4.7 |
|---|---|---|
| LMArena Instruction Following | — | 1411 |

## Long Context

- Claude Sonnet 5.5: —
- GLM-4.7: 42.8 (#111)

| Benchmark | Claude Sonnet 5.5 | GLM-4.7 |
|---|---|---|
| CL-bench | — | 15.9% |
| CL-bench Life | — | 10.9% |
| LMArena Longer Query | — | 1432 |

## Writing & Preference

- Claude Sonnet 5.5: —
- GLM-4.7: 61.1 (#89)

| Benchmark | Claude Sonnet 5.5 | GLM-4.7 |
|---|---|---|
| LMArena Text | — | 1436 |
| LMArena Creative Writing | — | 1401 |
| EQ-Bench Creative Writing | — | 1413 |
| LMArena Multi-Turn | — | 1446 |

## FAQ

### Is Claude Sonnet 5.5 better than GLM-4.7?

Claude Sonnet 5.5 is the stronger model overall, scoring 60.5 to 41.7 on the Noometry Index. GLM-4.7 costs 4.0× less per token, which makes it the better buy when Claude Sonnet 5.5's lead doesn't matter for your workload.

### Which is cheaper, Claude Sonnet 5.5 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; Claude Sonnet 5.5 lists at $2 and $10.

### Is Claude Sonnet 5.5 or GLM-4.7 better for coding?

Claude Sonnet 5.5 scores higher on coding benchmarks: 65.5 versus 43.6 in the Noometry coding category.

### Which has the bigger context window?

Claude Sonnet 5.5 does, with 1M tokens against 205K.

### How many benchmarks do Claude Sonnet 5.5 and GLM-4.7 share?

8 benchmarks have published results for both models. Claude Sonnet 5.5 has 16 scored results on Noometry and GLM-4.7 has 36.