# Claude 3 Sonnet vs GLM-4.6

> GLM-4.6 is the stronger model overall, scoring 40.9 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-sonnet-vs-glm-4-6
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and GLM-4.6 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.6 leads 36.4 to 10.0.
- GLM-4.6 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Sonnet | GLM-4.6 |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 28.8 | 40.9 |
| Rank | 311 | 132 |
| Context | — | 205K |
| Input $/M | — | $0.60 |
| Output $/M | — | $2.20 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Sonnet: 29.2 (#296)
- GLM-4.6: 39.9 (#137)

| Benchmark | Claude 3 Sonnet | GLM-4.6 |
|---|---|---|
| LMArena Coding | 1223 | 1449 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1339 |
| SciCode | — | 38.4% |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| ALE-Bench | — | 340.82 |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |

## Agentic & Tool Use

- Claude 3 Sonnet: —
- GLM-4.6: 32.1 (#60)

| Benchmark | Claude 3 Sonnet | GLM-4.6 |
|---|---|---|
| Terminal-Bench | — | 24.5% |
| Berkeley Function Calling Leaderboard | — | 72.4% |

## Reasoning

- Claude 3 Sonnet: 19.7 (#232)
- GLM-4.6: 23.1 (#168)

| Benchmark | Claude 3 Sonnet | GLM-4.6 |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1440 |
| Kagi LLM Benchmark | — | 47.4% |
| CritPt | — | 1.1% |
| DTBench | 53.6% | — |
| Epoch Capabilities Index | 120.69 | — |
| WinoGrande | 75.1% | — |

## Math

- Claude 3 Sonnet: 10.0 (#305)
- GLM-4.6: 36.4 (#115)

| Benchmark | Claude 3 Sonnet | GLM-4.6 |
|---|---|---|
| LMArena Math | 1213 | 1431 |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| MATH Level 5 | 18.2% | — |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Claude 3 Sonnet: 21.1 (#271)
- GLM-4.6: 39.6 (#118)

| Benchmark | Claude 3 Sonnet | GLM-4.6 |
|---|---|---|
| LMArena Expert | 1173 | 1432 |
| GPQA Diamond | 40.6% | — |
| Vectara Hallucination Rate | — | 9.5% |
| MMLU | 75.9% | — |

## Multimodal

- Claude 3 Sonnet: 24.7 (#120)
- GLM-4.6: —

| Benchmark | Claude 3 Sonnet | GLM-4.6 |
|---|---|---|
| LMArena Vision | 984 | — |

## Multilingual

- Claude 3 Sonnet: 38.0 (#229)
- GLM-4.6: 53.6 (#62)

| Benchmark | Claude 3 Sonnet | GLM-4.6 |
|---|---|---|
| LMArena Non-English | 1205 | 1426 |
| LMArena Chinese | 1188 | 1500 |
| LMArena French | 1228 | 1459 |
| LMArena German | 1204 | 1447 |
| LMArena Japanese | 1131 | 1394 |
| LMArena Korean | 1128 | 1401 |
| LMArena Russian | 1227 | 1418 |
| LMArena Spanish | 1204 | 1436 |

## Instruction Following

- Claude 3 Sonnet: 63.1 (#230)
- GLM-4.6: 74.5 (#93)

| Benchmark | Claude 3 Sonnet | GLM-4.6 |
|---|---|---|
| LMArena Instruction Following | 1200 | 1410 |

## Long Context

- Claude 3 Sonnet: 36.7 (#223)
- GLM-4.6: 43.4 (#91)

| Benchmark | Claude 3 Sonnet | GLM-4.6 |
|---|---|---|
| LMArena Longer Query | 1211 | 1423 |

## Writing & Preference

- Claude 3 Sonnet: 42.3 (#233)
- GLM-4.6: 61.3 (#86)

| Benchmark | Claude 3 Sonnet | GLM-4.6 |
|---|---|---|
| LMArena Text | 1218 | 1440 |
| LMArena Creative Writing | 1186 | 1411 |
| LMArena Multi-Turn | 1227 | 1427 |
| EQ-Bench Creative Writing | — | 1411 |

## FAQ

### Is Claude 3 Sonnet better than GLM-4.6?

GLM-4.6 is the stronger model overall, scoring 40.9 to 28.8 on the Noometry Index.

### Is Claude 3 Sonnet or GLM-4.6 better for coding?

GLM-4.6 scores higher on coding benchmarks: 39.9 versus 29.2 in the Noometry coding category.

### How many benchmarks do Claude 3 Sonnet and GLM-4.6 share?

17 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and GLM-4.6 has 29.