# GLM-5.1 vs Llama 3-8B

> GLM-5.1 is the stronger model overall, scoring 47.6 to 25.3 on the Noometry Index. Llama 3-8B costs 15× 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-3-8b
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and Llama 3-8B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.1 leads 55.0 to 7.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 and 1.9% for Llama 3-8B.
- Llama 3-8B is cheaper at $0.14 / $0.14 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- GLM-5.1 accepts more context: 200K tokens versus 8K.

## Snapshot

| | GLM-5.1 | Llama 3-8B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 47.6 | 25.3 |
| Rank | 51 | 338 |
| Context | 200K | 8K |
| Input $/M | $1.40 | $0.14 |
| Output $/M | $4.40 | $0.14 |
| Weights | Open | Open |

## Coding

- GLM-5.1: 48.5 (#52)
- Llama 3-8B: 30.5 (#285)

| Benchmark | GLM-5.1 | Llama 3-8B |
|---|---|---|
| LMArena Coding | 1486 | 1152 |
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1509 | — |
| SciCode | 43.8% | — |
| WeirdML | 57.1% | — |
| BigCodeBench Instruct | — | 31.9% |
| BigCodeBench Complete | — | 36.9% |
| ALE-Bench | 887.1 | — |
| HumanEval+ | — | 56.7% |
| MBPP+ | — | 54.8% |

## Agentic & Tool Use

- GLM-5.1: 24.8 (#106)
- Llama 3-8B: —

| Benchmark | GLM-5.1 | Llama 3-8B |
|---|---|---|
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 38.2 (#57)
- Llama 3-8B: 13.8 (#321)

| Benchmark | GLM-5.1 | Llama 3-8B |
|---|---|---|
| Chess Puzzles | 19% | 0% |
| LMArena Hard Prompts | 1472 | 1133 |
| Epoch Capabilities Index | 149.86 | 116.33 |
| SimpleBench | 55.1% | — |
| NYT Connections (extended) | 77.7% | — |
| CritPt | 4.6% | — |
| Thematic Generalization | 69.8% | — |
| DTBench | — | 43.9% |
| Adversarial NLI | — | 57.3% |
| ForecastBench | — | 58.6 |
| WinoGrande | — | 75.7% |

## Math

- GLM-5.1: 49.0 (#48)
- Llama 3-8B: 8.3 (#317)

| Benchmark | GLM-5.1 | Llama 3-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 1.9% |
| LMArena Math | 1472 | 1151 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| MATH Level 5 | — | 6.1% |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GLM-5.1: 55.0 (#45)
- Llama 3-8B: 7.8 (#303)

| Benchmark | GLM-5.1 | Llama 3-8B |
|---|---|---|
| GPQA Diamond | 89.9% | 26.1% |
| LMArena Expert | 1477 | 1113 |
| SimpleQA Verified | 34% | — |
| ARC (AI2) Challenge | — | 82.8% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 82.6% |
| TriviaQA | — | 67.7% |

## Multilingual

- GLM-5.1: 55.2 (#34)
- Llama 3-8B: 31.0 (#256)

| Benchmark | GLM-5.1 | Llama 3-8B |
|---|---|---|
| LMArena Non-English | 1448 | 1098 |
| LMArena Chinese | 1516 | 1076 |
| LMArena French | 1478 | 1158 |
| LMArena German | 1466 | 1104 |
| LMArena Japanese | 1436 | 967 |
| LMArena Korean | 1423 | 1003 |
| LMArena Russian | 1453 | 1109 |
| LMArena Spanish | 1467 | 1172 |

## Instruction Following

- GLM-5.1: 76.5 (#41)
- Llama 3-8B: 58.7 (#255)

| Benchmark | GLM-5.1 | Llama 3-8B |
|---|---|---|
| LMArena Instruction Following | 1451 | 1127 |

## Long Context

- GLM-5.1: 44.9 (#51)
- Llama 3-8B: 34.2 (#246)

| Benchmark | GLM-5.1 | Llama 3-8B |
|---|---|---|
| LMArena Longer Query | 1467 | 1128 |

## Writing & Preference

- GLM-5.1: 67.2 (#29)
- Llama 3-8B: 37.7 (#251)

| Benchmark | GLM-5.1 | Llama 3-8B |
|---|---|---|
| LMArena Text | 1462 | 1166 |
| LMArena Creative Writing | 1454 | 1150 |
| LMArena Multi-Turn | 1473 | 1152 |
| EQ-Bench Creative Writing | 1592 | — |

## FAQ

### Is GLM-5.1 better than Llama 3-8B?

GLM-5.1 is the stronger model overall, scoring 47.6 to 25.3 on the Noometry Index. Llama 3-8B costs 15× 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 3-8B?

Llama 3-8B is cheaper. It lists at $0.14 per million input tokens and $0.14 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.

### Is GLM-5.1 or Llama 3-8B better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.5 versus 30.5 in the Noometry coding category.

### Which has the bigger context window?

GLM-5.1 does, with 200K tokens against 8K.

### How many benchmarks do GLM-5.1 and Llama 3-8B share?

21 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Llama 3-8B has 34.