# GLM-5.1 vs Llama 3.1-8B

> GLM-5.1 is the stronger model overall, scoring 47.8 to 23.0 on the Noometry Index. Llama 3.1-8B costs 37× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-llama-3-1-8b
- Last updated: 2026-10-12
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. GLM-5.1 scores higher in 9 categories and Llama 3.1-8B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.1 leads 54.9 to 8.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 and 1.7% for Llama 3.1-8B.
- Llama 3.1-8B is cheaper at $0.05 / $0.08 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- GLM-5.1 accepts more context: 200K tokens versus 128K.

## Snapshot

| | GLM-5.1 | Llama 3.1-8B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 47.8 | 23.0 |
| Rank | 59 | 352 |
| Context | 200K | 128K |
| Input $/M | $1.40 | $0.05 |
| Output $/M | $4.40 | $0.08 |
| Weights | Open | Open |

## Coding

- GLM-5.1: 48.7 (#55)
- Llama 3.1-8B: 20.2 (#340)

| Benchmark | GLM-5.1 | Llama 3.1-8B |
|---|---|---|
| SciCode | 43.8% | 13.2% |
| WeirdML | 57.1% | 1.7% |
| LMArena Coding | 1485 | 1195 |
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1508 | — |
| BigCodeBench Instruct | — | 32.8% |
| BigCodeBench Complete | — | 40.5% |
| ALE-Bench | 887.1 | — |
| HumanEval+ | — | 62.8% |
| MBPP+ | — | 55.6% |

## Agentic & Tool Use

- GLM-5.1: 24.9 (#113)
- Llama 3.1-8B: 22.5 (#131)

| Benchmark | GLM-5.1 | Llama 3.1-8B |
|---|---|---|
| APEX-Agents | 40.9% | — |
| Berkeley Function Calling Leaderboard | — | 25.8% |
| BALROG | — | 15.1% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 39.1 (#60)
- Llama 3.1-8B: 14.9 (#321)

| Benchmark | GLM-5.1 | Llama 3.1-8B |
|---|---|---|
| CritPt | 4.6% | 0% |
| Chess Puzzles | 19% | 0% |
| LMArena Hard Prompts | 1472 | 1175 |
| Epoch Capabilities Index | 149.84 | 116.57 |
| SimpleBench | 55.1% | — |
| NYT Connections (extended) | 77.7% | — |
| Thematic Generalization | 69.8% | — |
| DTBench | — | 50.9% |
| LMCA | — | 5.4% |
| PIQA | — | 81.2% |

## Math

- GLM-5.1: 49.7 (#60)
- Llama 3.1-8B: 10.2 (#317)

| Benchmark | GLM-5.1 | Llama 3.1-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 1.7% |
| LMArena Math | 1473 | 1179 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| Omni-MATH | — | 13.7% |
| MATH Level 5 | — | 22.9% |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
| GSM8K | — | 82.4% |

## Knowledge

- GLM-5.1: 54.9 (#50)
- Llama 3.1-8B: 8.0 (#307)

| Benchmark | GLM-5.1 | Llama 3.1-8B |
|---|---|---|
| GPQA Diamond | 89.9% | 27% |
| LMArena Expert | 1476 | 1144 |
| SimpleQA Verified | 34% | — |
| MMLU-Pro | — | 40.6% |
| GPQA (HELM) | — | 24.7% |
| BoolQ | — | 82.8% |
| MMLU | — | 56.1% |

## Multilingual

- GLM-5.1: 55.0 (#36)
- Llama 3.1-8B: 34.0 (#249)

| Benchmark | GLM-5.1 | Llama 3.1-8B |
|---|---|---|
| LMArena Non-English | 1447 | 1148 |
| LMArena Chinese | 1515 | 1151 |
| LMArena French | 1474 | 1177 |
| LMArena German | 1465 | 1144 |
| LMArena Japanese | 1434 | 1061 |
| LMArena Korean | 1418 | 1053 |
| LMArena Russian | 1454 | 1158 |
| LMArena Spanish | 1469 | 1169 |

## Instruction Following

- GLM-5.1: 76.3 (#42)
- Llama 3.1-8B: 58.9 (#258)

| Benchmark | GLM-5.1 | Llama 3.1-8B |
|---|---|---|
| LMArena Instruction Following | 1451 | 1159 |
| IFEval | — | 74.3% |

## Long Context

- GLM-5.1: 44.9 (#53)
- Llama 3.1-8B: 35.8 (#238)

| Benchmark | GLM-5.1 | Llama 3.1-8B |
|---|---|---|
| LMArena Longer Query | 1466 | 1182 |

## Writing & Preference

- GLM-5.1: 66.9 (#31)
- Llama 3.1-8B: 29.7 (#290)

| Benchmark | GLM-5.1 | Llama 3.1-8B |
|---|---|---|
| LMArena Text | 1461 | 1187 |
| LMArena Creative Writing | 1453 | 1154 |
| EQ-Bench Creative Writing | 1592 | 713 |
| LMArena Multi-Turn | 1472 | 1172 |
| WildBench | — | 68.7% |

## FAQ

### Is GLM-5.1 better than Llama 3.1-8B?

GLM-5.1 is the stronger model overall, scoring 47.8 to 23.0 on the Noometry Index. Llama 3.1-8B costs 37× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.

### Which is cheaper, GLM-5.1 or Llama 3.1-8B?

Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.

### Is GLM-5.1 or Llama 3.1-8B better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.7 versus 20.2 in the Noometry coding category.

### Which has the bigger context window?

GLM-5.1 does, with 200K tokens against 128K.

### How many benchmarks do GLM-5.1 and Llama 3.1-8B share?

25 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Llama 3.1-8B has 43.