# Claude 3 Sonnet vs GLM-4.7

> GLM-4.7 is the stronger model overall, scoring 42.0 to 29.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-sonnet-vs-glm-4-7
- Last updated: 2026-10-11
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and GLM-4.7 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.7 leads 38.6 to 10.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 83.3% for GLM-4.7.
- GLM-4.7 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Sonnet | GLM-4.7 |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 29.0 | 42.0 |
| Rank | 319 | 124 |
| Context | — | 205K |
| Input $/M | — | $0.60 |
| Output $/M | — | $2.20 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Sonnet: 29.6 (#302)
- GLM-4.7: 44.0 (#79)

| Benchmark | Claude 3 Sonnet | GLM-4.7 |
|---|---|---|
| LMArena Coding | 1223 | 1454 |
| LMArena WebDev | — | 1435 |
| SciCode | — | 45.1% |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| ALE-Bench | — | 399.48 |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |

## Agentic & Tool Use

- Claude 3 Sonnet: —
- GLM-4.7: 26.5 (#103)

| Benchmark | Claude 3 Sonnet | GLM-4.7 |
|---|---|---|
| Terminal-Bench | — | 33.4% |
| Vending-Bench 2 | — | 2,377 |

## Reasoning

- Claude 3 Sonnet: 20.5 (#237)
- GLM-4.7: 24.3 (#164)

| Benchmark | Claude 3 Sonnet | GLM-4.7 |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1443 |
| Epoch Capabilities Index | 120.7 | 143.51 |
| SimpleBench | — | 47.7% |
| CritPt | — | 1.7% |
| Chess Puzzles | — | 6% |
| DTBench | 53.6% | — |
| WinoGrande | 75.1% | — |

## Math

- Claude 3 Sonnet: 10.7 (#310)
- GLM-4.7: 38.6 (#135)

| Benchmark | Claude 3 Sonnet | GLM-4.7 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 83.3% |
| LMArena Math | 1213 | 1423 |
| ProofBench | — | 6% |
| MATH Level 5 | 18.2% | — |
| FrontierMath (Feb 2025 set) | — | 2.4% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Claude 3 Sonnet: 21.1 (#276)
- GLM-4.7: 47.0 (#80)

| Benchmark | Claude 3 Sonnet | GLM-4.7 |
|---|---|---|
| GPQA Diamond | 40.6% | 83.3% |
| LMArena Expert | 1173 | 1424 |
| SimpleQA Verified | — | 32.2% |
| Vectara Hallucination Rate | — | 11.7% |
| MMLU | 75.9% | — |

## Multimodal

- Claude 3 Sonnet: 25.2 (#125)
- GLM-4.7: —

| Benchmark | Claude 3 Sonnet | GLM-4.7 |
|---|---|---|
| LMArena Vision | 984 | — |

## Multilingual

- Claude 3 Sonnet: 37.8 (#234)
- GLM-4.7: 52.8 (#79)

| Benchmark | Claude 3 Sonnet | GLM-4.7 |
|---|---|---|
| LMArena Non-English | 1205 | 1417 |
| LMArena Chinese | 1189 | 1495 |
| LMArena French | 1229 | 1432 |
| LMArena German | 1204 | 1424 |
| LMArena Japanese | 1131 | 1439 |
| LMArena Korean | 1128 | 1399 |
| LMArena Russian | 1227 | 1423 |
| LMArena Spanish | 1204 | 1434 |

## Instruction Following

- Claude 3 Sonnet: 62.8 (#235)
- GLM-4.7: 74.4 (#95)

| Benchmark | Claude 3 Sonnet | GLM-4.7 |
|---|---|---|
| LMArena Instruction Following | 1199 | 1411 |

## Long Context

- Claude 3 Sonnet: 36.7 (#228)
- GLM-4.7: 42.8 (#116)

| Benchmark | Claude 3 Sonnet | GLM-4.7 |
|---|---|---|
| LMArena Longer Query | 1211 | 1432 |
| CL-bench | — | 15.9% |
| CL-bench Life | — | 10.9% |

## Writing & Preference

- Claude 3 Sonnet: 42.1 (#238)
- GLM-4.7: 60.9 (#93)

| Benchmark | Claude 3 Sonnet | GLM-4.7 |
|---|---|---|
| LMArena Text | 1218 | 1435 |
| LMArena Creative Writing | 1186 | 1401 |
| LMArena Multi-Turn | 1227 | 1446 |
| EQ-Bench Creative Writing | — | 1413 |

## FAQ

### Is Claude 3 Sonnet better than GLM-4.7?

GLM-4.7 is the stronger model overall, scoring 42.0 to 29.0 on the Noometry Index.

### Is Claude 3 Sonnet or GLM-4.7 better for coding?

GLM-4.7 scores higher on coding benchmarks: 44.0 versus 29.6 in the Noometry coding category.

### How many benchmarks do Claude 3 Sonnet and GLM-4.7 share?

20 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and GLM-4.7 has 36.