# Claude Sonnet 4.6 vs GLM-5.3

> GLM-5.3 is the stronger model overall, scoring 54.8 to 50.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-6-vs-glm-5-3
- Last updated: 2026-10-10
- Shared benchmarks: 37

## Summary

- They share 37 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 2 categories and GLM-5.3 in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where GLM-5.3 leads 59.5 to 46.3.
- The biggest single-benchmark swing is DeepSWE: 29.9% for Claude Sonnet 4.6 and 69% for GLM-5.3.
- GLM-5.3 is cheaper at $1.40 / $4.40 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
- GLM-5.3 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 4.6 | GLM-5.3 |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 50.3 | 54.8 |
| Rank | 50 | 26 |
| Context | 1M | 1M |
| Input $/M | $3 | $1.40 |
| Output $/M | $15 | $4.40 |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 4.6: 46.3 (#67)
- GLM-5.3: 59.5 (#14)

| Benchmark | Claude Sonnet 4.6 | GLM-5.3 |
|---|---|---|
| DeepSWE | 29.9% | 69% |
| FrontierCode | 24.3% | 40.1% |
| LMArena WebDev | 1522 | 1622 |
| SciCode | 46.8% | 59% |
| WeirdML | 66.1% | 75.4% |
| LMArena Coding | 1504 | 1496 |
| ALE-Bench | 1,327 | 1,317 |
| SWE-bench Verified | 75.2% | — |
| CursorBench | — | 42.6% |
| FrontierSWE | — | 30.2% |

## Agentic & Tool Use

- Claude Sonnet 4.6: 39.1 (#28)
- GLM-5.3: 36.4 (#38)

| Benchmark | Claude Sonnet 4.6 | GLM-5.3 |
|---|---|---|
| APEX-Agents | 43% | 56.6% |
| Vending-Bench 2 | 7,204 | 8,164 |
| Terminal-Bench | 53.4% | — |
| OSWorld 2.0 | 9.3% | — |
| DeepResearch Bench | 54.9% | — |
| OSWorld | 72.1% | — |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
| GDP.pdf | 18% | — |
| LMArena Search | 1221 | — |

## Reasoning

- Claude Sonnet 4.6: 46.1 (#45)
- GLM-5.3: 46.1 (#46)

| Benchmark | Claude Sonnet 4.6 | GLM-5.3 |
|---|---|---|
| NYT Connections (extended) | 80.9% | 74.2% |
| CritPt | 3.1% | 19.1% |
| Chess Puzzles | 13% | 21% |
| LMArena Hard Prompts | 1484 | 1489 |
| Mystery Game Puzzles | 16% | 33% |
| DTBench | 89.9% | 87.7% |
| LMCA | 46.5% | 55.5% |
| Epoch Capabilities Index | 152.24 | 155.61 |
| ARC-AGI-2 | 60.4% | — |
| ARC-AGI-1 | 86.5% | — |
| Thematic Generalization | 76.3% | — |
| Bench to the Future 3 | — | 0.15 |
| ForecastBench | 62 | — |

## Math

- Claude Sonnet 4.6: 52.9 (#49)
- GLM-5.3: 62.3 (#33)

| Benchmark | Claude Sonnet 4.6 | GLM-5.3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | 91.1% |
| ProofBench | 45% | 49% |
| LMArena Math | 1462 | 1489 |
| FrontierMath (Tiers 1-3) | — | 68.8% |
| FrontierMath Tier 4 | — | 29.3% |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 8.3% | — |

## Knowledge

- Claude Sonnet 4.6: 51.7 (#65)
- GLM-5.3: 58.3 (#37)

| Benchmark | Claude Sonnet 4.6 | GLM-5.3 |
|---|---|---|
| GPQA Diamond | 87.4% | 90.9% |
| SimpleQA Verified | 35.5% | 41% |
| LMArena Expert | 1500 | 1516 |
| Vectara Hallucination Rate | 10.6% | — |

## Multimodal

- Claude Sonnet 4.6: 38.0 (#68)
- GLM-5.3: —

| Benchmark | Claude Sonnet 4.6 | GLM-5.3 |
|---|---|---|
| LMArena Vision | 1283 | — |
| Blueprint-Bench 2 | 6.7% | — |
| LMArena Document | 1482 | — |

## Multilingual

- Claude Sonnet 4.6: 54.4 (#41)
- GLM-5.3: 55.7 (#28)

| Benchmark | Claude Sonnet 4.6 | GLM-5.3 |
|---|---|---|
| LMArena Non-English | 1440 | 1457 |
| LMArena Chinese | 1491 | 1528 |
| LMArena French | 1465 | 1499 |
| LMArena German | 1428 | 1499 |
| LMArena Japanese | 1420 | 1453 |
| LMArena Korean | 1411 | 1472 |
| LMArena Russian | 1440 | 1463 |
| LMArena Spanish | 1464 | 1460 |

## Instruction Following

- Claude Sonnet 4.6: 77.4 (#25)
- GLM-5.3: 77.5 (#23)

| Benchmark | Claude Sonnet 4.6 | GLM-5.3 |
|---|---|---|
| LMArena Instruction Following | 1475 | 1477 |

## Long Context

- Claude Sonnet 4.6: 45.3 (#44)
- GLM-5.3: 45.4 (#41)

| Benchmark | Claude Sonnet 4.6 | GLM-5.3 |
|---|---|---|
| LMArena Longer Query | 1479 | 1482 |

## Writing & Preference

- Claude Sonnet 4.6: 70.2 (#22)
- GLM-5.3: 75.7 (#6)

| Benchmark | Claude Sonnet 4.6 | GLM-5.3 |
|---|---|---|
| LMArena Text | 1458 | 1471 |
| LMArena Creative Writing | 1435 | 1457 |
| EQ-Bench Creative Writing | 1810 | 2075 |
| LMArena Multi-Turn | 1464 | 1472 |
| EQ-Bench 4 | 1207 | — |

## FAQ

### Is Claude Sonnet 4.6 better than GLM-5.3?

GLM-5.3 is the stronger model overall, scoring 54.8 to 50.3 on the Noometry Index.

### Which is cheaper, Claude Sonnet 4.6 or GLM-5.3?

GLM-5.3 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.

### Is Claude Sonnet 4.6 or GLM-5.3 better for coding?

GLM-5.3 scores higher on coding benchmarks: 59.5 versus 46.3 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1M tokens.

### How many benchmarks do Claude Sonnet 4.6 and GLM-5.3 share?

37 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and GLM-5.3 has 42.