# Claude 3 Sonnet vs GLM-5.3

> GLM-5.3 is the stronger model overall, scoring 54.6 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-sonnet-vs-glm-5-3
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and GLM-5.3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.3 leads 62.1 to 10.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 91.1% for GLM-5.3.
- GLM-5.3 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Sonnet | GLM-5.3 |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 28.8 | 54.6 |
| Rank | 311 | 25 |
| Context | — | 1M |
| Input $/M | — | $1.40 |
| Output $/M | — | $4.40 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Sonnet: 29.2 (#296)
- GLM-5.3: 59.0 (#12)

| Benchmark | Claude 3 Sonnet | GLM-5.3 |
|---|---|---|
| WeirdML | 10.2% | 75.4% |
| LMArena Coding | 1223 | 1499 |
| DeepSWE | — | 69% |
| FrontierCode | — | 40.1% |
| LMArena WebDev | — | 1623 |
| FrontierSWE | — | 30.2% |
| SciCode | — | 59% |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| ALE-Bench | — | 1,317 |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |

## Agentic & Tool Use

- Claude 3 Sonnet: —
- GLM-5.3: 36.3 (#34)

| Benchmark | Claude 3 Sonnet | GLM-5.3 |
|---|---|---|
| APEX-Agents | — | 56.6% |
| Vending-Bench 2 | — | 8,164 |

## Reasoning

- Claude 3 Sonnet: 19.7 (#232)
- GLM-5.3: 45.2 (#42)

| Benchmark | Claude 3 Sonnet | GLM-5.3 |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1491 |
| DTBench | 53.6% | 87.7% |
| Epoch Capabilities Index | 120.69 | 155.56 |
| NYT Connections (extended) | — | 74.2% |
| CritPt | — | 19.1% |
| Chess Puzzles | — | 21% |
| Mystery Game Puzzles | — | 33% |
| LMCA | — | 55.5% |
| Bench to the Future 3 | — | 0.15 |
| WinoGrande | 75.1% | — |

## Math

- Claude 3 Sonnet: 10.0 (#305)
- GLM-5.3: 62.1 (#27)

| Benchmark | Claude 3 Sonnet | GLM-5.3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 91.1% |
| LMArena Math | 1213 | 1493 |
| FrontierMath (Tiers 1-3) | — | 68.8% |
| FrontierMath Tier 4 | — | 29.3% |
| ProofBench | — | 49% |
| MATH Level 5 | 18.2% | — |

## Knowledge

- Claude 3 Sonnet: 21.1 (#271)
- GLM-5.3: 58.3 (#34)

| Benchmark | Claude 3 Sonnet | GLM-5.3 |
|---|---|---|
| GPQA Diamond | 40.6% | 90.9% |
| LMArena Expert | 1173 | 1512 |
| SimpleQA Verified | — | 41% |
| MMLU | 75.9% | — |

## Multimodal

- Claude 3 Sonnet: 24.7 (#120)
- GLM-5.3: —

| Benchmark | Claude 3 Sonnet | GLM-5.3 |
|---|---|---|
| LMArena Vision | 984 | — |

## Multilingual

- Claude 3 Sonnet: 38.0 (#229)
- GLM-5.3: 55.9 (#27)

| Benchmark | Claude 3 Sonnet | GLM-5.3 |
|---|---|---|
| LMArena Non-English | 1205 | 1457 |
| LMArena Chinese | 1188 | 1523 |
| LMArena French | 1228 | 1499 |
| LMArena German | 1204 | 1505 |
| LMArena Japanese | 1131 | 1438 |
| LMArena Korean | 1128 | 1478 |
| LMArena Russian | 1227 | 1460 |
| LMArena Spanish | 1204 | 1444 |

## Instruction Following

- Claude 3 Sonnet: 63.1 (#230)
- GLM-5.3: 77.8 (#15)

| Benchmark | Claude 3 Sonnet | GLM-5.3 |
|---|---|---|
| LMArena Instruction Following | 1200 | 1481 |

## Long Context

- Claude 3 Sonnet: 36.7 (#223)
- GLM-5.3: 45.5 (#32)

| Benchmark | Claude 3 Sonnet | GLM-5.3 |
|---|---|---|
| LMArena Longer Query | 1211 | 1485 |

## Writing & Preference

- Claude 3 Sonnet: 42.3 (#233)
- GLM-5.3: 75.9 (#6)

| Benchmark | Claude 3 Sonnet | GLM-5.3 |
|---|---|---|
| LMArena Text | 1218 | 1473 |
| LMArena Creative Writing | 1186 | 1459 |
| LMArena Multi-Turn | 1227 | 1473 |
| EQ-Bench Creative Writing | — | 2075 |

## FAQ

### Is Claude 3 Sonnet better than GLM-5.3?

GLM-5.3 is the stronger model overall, scoring 54.6 to 28.8 on the Noometry Index.

### Is Claude 3 Sonnet or GLM-5.3 better for coding?

GLM-5.3 scores higher on coding benchmarks: 59.0 versus 29.2 in the Noometry coding category.

### How many benchmarks do Claude 3 Sonnet and GLM-5.3 share?

22 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and GLM-5.3 has 41.