# GLM-4.5 vs Llama 3.1-405B

> GLM-4.5 is the stronger model overall, scoring 42.0 to 30.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-5-vs-llama-3-1-405b
- Last updated: 2026-10-12
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. GLM-4.5 scores higher in 7 categories and Llama 3.1-405B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.5 leads 39.0 to 18.4.
- The biggest single-benchmark swing is WeirdML: 40.6% for GLM-4.5 and 21.4% for Llama 3.1-405B.

## Snapshot

| | GLM-4.5 | Llama 3.1-405B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 42.0 | 30.7 |
| Rank | 122 | 288 |
| Context | 131K | — |
| Input $/M | $0.60 | — |
| Output $/M | $2.20 | — |
| Weights | Open | Open |

## Coding

- GLM-4.5: 41.4 (#125)
- Llama 3.1-405B: 33.1 (#262)

| Benchmark | GLM-4.5 | Llama 3.1-405B |
|---|---|---|
| WeirdML | 40.6% | 21.4% |
| LMArena Coding | 1434 | 1291 |
| SWE-bench Verified (bash only) | 54.2% | — |
| ALE-Bench | 344.82 | — |
| AlgoTune | 1.52 | — |

## Agentic & Tool Use

- GLM-4.5: —
- Llama 3.1-405B: 21.0 (#140)

| Benchmark | GLM-4.5 | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |

## Reasoning

- GLM-4.5: 28.6 (#100)
- Llama 3.1-405B: 16.8 (#300)

| Benchmark | GLM-4.5 | Llama 3.1-405B |
|---|---|---|
| Kagi LLM Benchmark | 57.9% | 45% |
| LMArena Hard Prompts | 1429 | 1269 |
| SimpleBench | — | 23% |
| DTBench | — | 61.4% |
| BIG-Bench Hard | — | 82.9% |
| Epoch Capabilities Index | — | 128.75 |
| ForecastBench | — | 59.9 |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |

## Math

- GLM-4.5: 39.0 (#116)
- Llama 3.1-405B: 18.4 (#290)

| Benchmark | GLM-4.5 | Llama 3.1-405B |
|---|---|---|
| LMArena Math | 1427 | 1281 |
| OTIS Mock AIME 2024-2025 | — | 9.7% |
| Omni-MATH | — | 24.9% |
| MATH Level 5 | — | 49.8% |

## Knowledge

- GLM-4.5: 35.9 (#179)
- Llama 3.1-405B: 30.4 (#227)

| Benchmark | GLM-4.5 | Llama 3.1-405B |
|---|---|---|
| Confabulations | 11.3% | 17.6% |
| LMArena Expert | 1433 | 1243 |
| GPQA Diamond | — | 50.9% |
| Humanity's Last Exam | 8.3% | — |
| MMLU-Pro | — | 72.3% |
| GPQA (HELM) | — | 52.2% |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |

## Multilingual

- GLM-4.5: 52.8 (#77)
- Llama 3.1-405B: 40.7 (#214)

| Benchmark | GLM-4.5 | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1417 | 1248 |
| LMArena Chinese | 1465 | 1242 |
| LMArena French | 1418 | 1279 |
| LMArena German | 1407 | 1252 |
| LMArena Japanese | 1415 | 1208 |
| LMArena Korean | 1380 | 1184 |
| LMArena Russian | 1414 | 1265 |
| LMArena Spanish | 1454 | 1260 |

## Instruction Following

- GLM-4.5: 74.1 (#104)
- Llama 3.1-405B: 65.9 (#214)

| Benchmark | GLM-4.5 | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1404 | 1259 |
| IFEval | — | 81.1% |

## Long Context

- GLM-4.5: 38.2 (#201)
- Llama 3.1-405B: 38.4 (#197)

| Benchmark | GLM-4.5 | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1412 | 1266 |
| Fiction.LiveBench | 58.3% | — |

## Writing & Preference

- GLM-4.5: 57.5 (#127)
- Llama 3.1-405B: 38.9 (#251)

| Benchmark | GLM-4.5 | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1430 | 1284 |
| LMArena Creative Writing | 1395 | 1262 |
| EQ-Bench Creative Writing | 1343 | 870 |
| LMArena Multi-Turn | 1415 | 1297 |
| Short-Story Creative Writing | 73.4% | — |
| WildBench | — | 78.3% |

## FAQ

### Is GLM-4.5 better than Llama 3.1-405B?

GLM-4.5 is the stronger model overall, scoring 42.0 to 30.7 on the Noometry Index.

### Is GLM-4.5 or Llama 3.1-405B better for coding?

GLM-4.5 scores higher on coding benchmarks: 41.4 versus 33.1 in the Noometry coding category.

### How many benchmarks do GLM-4.5 and Llama 3.1-405B share?

21 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Llama 3.1-405B has 42.