# Claude 2.1 vs GLM-4.6

> GLM-4.6 is the stronger model overall, scoring 41.4 to 25.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-1-vs-glm-4-6
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where GLM-4.6 leads 39.1 to 10.2.
- GLM-4.6 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 2.1 | GLM-4.6 |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 25.2 | 41.4 |
| Rank | 345 | 135 |
| Context | — | 205K |
| Input $/M | — | $0.60 |
| Output $/M | — | $2.20 |
| Weights | Proprietary | Open |

## Coding

- Claude 2.1: 26.2 (#327)
- GLM-4.6: 40.1 (#148)

| Benchmark | Claude 2.1 | GLM-4.6 |
|---|---|---|
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1340 |
| SciCode | — | 38.4% |
| WeirdML | 7.1% | — |
| LMArena Coding | — | 1449 |
| ALE-Bench | — | 340.82 |

## Agentic & Tool Use

- Claude 2.1: —
- GLM-4.6: 32.3 (#66)

| Benchmark | Claude 2.1 | GLM-4.6 |
|---|---|---|
| Terminal-Bench | — | 24.5% |
| Berkeley Function Calling Leaderboard | — | 72.4% |

## Reasoning

- Claude 2.1: 21.4 (#221)
- GLM-4.6: 23.7 (#172)

| Benchmark | Claude 2.1 | GLM-4.6 |
|---|---|---|
| Kagi LLM Benchmark | — | 47.4% |
| CritPt | — | 1.1% |
| LMArena Hard Prompts | — | 1440 |
| DTBench | 51% | — |
| Epoch Capabilities Index | 119.27 | — |
| ForecastBench | 54.2 | — |

## Math

- Claude 2.1: 10.2 (#315)
- GLM-4.6: 39.1 (#111)

| Benchmark | Claude 2.1 | GLM-4.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| LMArena Math | — | 1432 |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Claude 2.1: 15.4 (#292)
- GLM-4.6: 40.2 (#124)

| Benchmark | Claude 2.1 | GLM-4.6 |
|---|---|---|
| GPQA Diamond | 33% | — |
| Vectara Hallucination Rate | — | 9.5% |
| LMArena Expert | — | 1431 |
| MMLU | 73.5% | — |

## Multilingual

- Claude 2.1: —
- GLM-4.6: 53.5 (#66)

| Benchmark | Claude 2.1 | GLM-4.6 |
|---|---|---|
| LMArena Non-English | — | 1426 |
| LMArena Chinese | — | 1499 |
| LMArena French | — | 1459 |
| LMArena German | — | 1447 |
| LMArena Japanese | — | 1393 |
| LMArena Korean | — | 1400 |
| LMArena Russian | — | 1419 |
| LMArena Spanish | — | 1436 |

## Instruction Following

- Claude 2.1: —
- GLM-4.6: 74.3 (#98)

| Benchmark | Claude 2.1 | GLM-4.6 |
|---|---|---|
| LMArena Instruction Following | — | 1410 |

## Long Context

- Claude 2.1: —
- GLM-4.6: 43.4 (#94)

| Benchmark | Claude 2.1 | GLM-4.6 |
|---|---|---|
| LMArena Longer Query | — | 1422 |

## Writing & Preference

- Claude 2.1: —
- GLM-4.6: 61.1 (#90)

| Benchmark | Claude 2.1 | GLM-4.6 |
|---|---|---|
| LMArena Text | — | 1440 |
| LMArena Creative Writing | — | 1411 |
| EQ-Bench Creative Writing | — | 1411 |
| LMArena Multi-Turn | — | 1427 |

## FAQ

### Is Claude 2.1 better than GLM-4.6?

GLM-4.6 is the stronger model overall, scoring 41.4 to 25.2 on the Noometry Index.

### Is Claude 2.1 or GLM-4.6 better for coding?

GLM-4.6 scores higher on coding benchmarks: 40.1 versus 26.2 in the Noometry coding category.

### How many benchmarks do Claude 2.1 and GLM-4.6 share?

0 benchmarks have published results for both models. Claude 2.1 has 7 scored results on Noometry and GLM-4.6 has 29.