# GLM-4.6 vs Llama 3.1-405B

> GLM-4.6 is the stronger model overall, scoring 40.9 to 30.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-6-vs-llama-3-1-405b
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. GLM-4.6 scores higher in 9 categories and Llama 3.1-405B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.6 leads 61.3 to 39.1.

## Snapshot

| | GLM-4.6 | Llama 3.1-405B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 40.9 | 30.4 |
| Rank | 132 | 279 |
| Context | 205K | — |
| Input $/M | $0.60 | — |
| Output $/M | $2.20 | — |
| Weights | Open | Open |

## Coding

- GLM-4.6: 39.9 (#137)
- Llama 3.1-405B: 32.7 (#257)

| Benchmark | GLM-4.6 | Llama 3.1-405B |
|---|---|---|
| LMArena Coding | 1449 | 1291 |
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1339 | — |
| SciCode | 38.4% | — |
| WeirdML | — | 21.4% |
| ALE-Bench | 340.82 | — |

## Agentic & Tool Use

- GLM-4.6: 32.1 (#60)
- Llama 3.1-405B: 20.9 (#131)

| Benchmark | GLM-4.6 | Llama 3.1-405B |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |

## Reasoning

- GLM-4.6: 23.1 (#168)
- Llama 3.1-405B: 16.4 (#293)

| Benchmark | GLM-4.6 | Llama 3.1-405B |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | 45% |
| LMArena Hard Prompts | 1440 | 1270 |
| SimpleBench | — | 23% |
| CritPt | 1.1% | — |
| DTBench | — | 61.4% |
| BIG-Bench Hard | — | 82.9% |
| Epoch Capabilities Index | — | 128.76 |
| ForecastBench | — | 59.9 |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |

## Math

- GLM-4.6: 36.4 (#115)
- Llama 3.1-405B: 17.3 (#283)

| Benchmark | GLM-4.6 | Llama 3.1-405B |
|---|---|---|
| LMArena Math | 1431 | 1281 |
| OTIS Mock AIME 2024-2025 | — | 9.7% |
| Omni-MATH | — | 24.9% |
| MATH Level 5 | — | 49.8% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GLM-4.6: 39.6 (#118)
- Llama 3.1-405B: 30.4 (#221)

| Benchmark | GLM-4.6 | Llama 3.1-405B |
|---|---|---|
| LMArena Expert | 1432 | 1243 |
| GPQA Diamond | — | 50.9% |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 17.6% |
| Vectara Hallucination Rate | 9.5% | — |
| GPQA (HELM) | — | 52.2% |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |

## Multilingual

- GLM-4.6: 53.6 (#62)
- Llama 3.1-405B: 40.9 (#209)

| Benchmark | GLM-4.6 | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1426 | 1248 |
| LMArena Chinese | 1500 | 1242 |
| LMArena French | 1459 | 1278 |
| LMArena German | 1447 | 1252 |
| LMArena Japanese | 1394 | 1208 |
| LMArena Korean | 1401 | 1184 |
| LMArena Russian | 1418 | 1265 |
| LMArena Spanish | 1436 | 1259 |

## Instruction Following

- GLM-4.6: 74.5 (#93)
- Llama 3.1-405B: 66.1 (#209)

| Benchmark | GLM-4.6 | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1410 | 1259 |
| IFEval | — | 81.1% |

## Long Context

- GLM-4.6: 43.4 (#91)
- Llama 3.1-405B: 38.4 (#192)

| Benchmark | GLM-4.6 | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1423 | 1266 |

## Writing & Preference

- GLM-4.6: 61.3 (#86)
- Llama 3.1-405B: 39.1 (#246)

| Benchmark | GLM-4.6 | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1440 | 1284 |
| LMArena Creative Writing | 1411 | 1262 |
| EQ-Bench Creative Writing | 1411 | 870 |
| LMArena Multi-Turn | 1427 | 1297 |
| WildBench | — | 78.3% |

## FAQ

### Is GLM-4.6 better than Llama 3.1-405B?

GLM-4.6 is the stronger model overall, scoring 40.9 to 30.4 on the Noometry Index.

### Is GLM-4.6 or Llama 3.1-405B better for coding?

GLM-4.6 scores higher on coding benchmarks: 39.9 versus 32.7 in the Noometry coding category.

### How many benchmarks do GLM-4.6 and Llama 3.1-405B share?

19 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Llama 3.1-405B has 42.