# GLM-5 vs Llama 3-8B

> GLM-5 is the stronger model overall, scoring 45.9 to 25.3 on the Noometry Index. Llama 3-8B costs 11× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-5-vs-llama-3-8b
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. GLM-5 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 leads 52.2 to 7.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 80% for GLM-5 and 1.9% for Llama 3-8B.
- Llama 3-8B is cheaper at $0.14 / $0.14 per million input/output tokens, against $1 / $3.20 for GLM-5.
- GLM-5 accepts more context: 205K tokens versus 8K.

## Snapshot

| | GLM-5 | Llama 3-8B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 45.9 | 25.3 |
| Rank | 59 | 338 |
| Context | 205K | 8K |
| Input $/M | $1 | $0.14 |
| Output $/M | $3.20 | $0.14 |
| Weights | Open | Open |

## Coding

- GLM-5: 49.0 (#47)
- Llama 3-8B: 30.5 (#285)

| Benchmark | GLM-5 | Llama 3-8B |
|---|---|---|
| LMArena Coding | 1461 | 1152 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| WeirdML | 48.2% | — |
| BigCodeBench Instruct | — | 31.9% |
| BigCodeBench Complete | — | 36.9% |
| ALE-Bench | 765.62 | — |
| HumanEval+ | — | 56.7% |
| MBPP+ | — | 54.8% |

## Agentic & Tool Use

- GLM-5: 30.9 (#65)
- Llama 3-8B: —

| Benchmark | GLM-5 | Llama 3-8B |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| Vending-Bench 2 | 4,432 | — |

## Reasoning

- GLM-5: 27.6 (#100)
- Llama 3-8B: 13.8 (#321)

| Benchmark | GLM-5 | Llama 3-8B |
|---|---|---|
| Chess Puzzles | 10% | 0% |
| LMArena Hard Prompts | 1451 | 1133 |
| Epoch Capabilities Index | 145.84 | 116.33 |
| ForecastBench | 61 | 58.6 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 53.2% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 74.8% | — |
| ARC-AGI-1 | 44.7% | — |
| DTBench | — | 43.9% |
| Adversarial NLI | — | 57.3% |
| WinoGrande | — | 75.7% |

## Math

- GLM-5: 44.8 (#66)
- Llama 3-8B: 8.3 (#317)

| Benchmark | GLM-5 | Llama 3-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 1.9% |
| LMArena Math | 1440 | 1151 |
| MathArena Final-Answer Competitions | 65.7% | — |
| MATH Level 5 | — | 6.1% |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GLM-5: 52.2 (#59)
- Llama 3-8B: 7.8 (#303)

| Benchmark | GLM-5 | Llama 3-8B |
|---|---|---|
| GPQA Diamond | 87.8% | 26.1% |
| LMArena Expert | 1454 | 1113 |
| Vectara Hallucination Rate | 10.1% | — |
| ARC (AI2) Challenge | — | 82.8% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 82.6% |
| TriviaQA | — | 67.7% |

## Multilingual

- GLM-5: 53.9 (#57)
- Llama 3-8B: 31.0 (#256)

| Benchmark | GLM-5 | Llama 3-8B |
|---|---|---|
| LMArena Non-English | 1430 | 1098 |
| LMArena Chinese | 1511 | 1076 |
| LMArena French | 1455 | 1158 |
| LMArena German | 1445 | 1104 |
| LMArena Japanese | 1416 | 967 |
| LMArena Korean | 1421 | 1003 |
| LMArena Russian | 1436 | 1109 |
| LMArena Spanish | 1452 | 1172 |

## Instruction Following

- GLM-5: 75.4 (#64)
- Llama 3-8B: 58.7 (#255)

| Benchmark | GLM-5 | Llama 3-8B |
|---|---|---|
| LMArena Instruction Following | 1427 | 1127 |

## Long Context

- GLM-5: 44.6 (#58)
- Llama 3-8B: 34.2 (#246)

| Benchmark | GLM-5 | Llama 3-8B |
|---|---|---|
| LMArena Longer Query | 1446 | 1128 |
| CL-bench | 18.7% | — |

## Writing & Preference

- GLM-5: 66.2 (#38)
- Llama 3-8B: 37.7 (#251)

| Benchmark | GLM-5 | Llama 3-8B |
|---|---|---|
| LMArena Text | 1446 | 1166 |
| LMArena Creative Writing | 1438 | 1150 |
| LMArena Multi-Turn | 1456 | 1152 |
| EQ-Bench Creative Writing | 1601 | — |

## FAQ

### Is GLM-5 better than Llama 3-8B?

GLM-5 is the stronger model overall, scoring 45.9 to 25.3 on the Noometry Index. Llama 3-8B costs 11× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.

### Which is cheaper, GLM-5 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 lists at $1 and $3.20.

### Is GLM-5 or Llama 3-8B better for coding?

GLM-5 scores higher on coding benchmarks: 49.0 versus 30.5 in the Noometry coding category.

### Which has the bigger context window?

GLM-5 does, with 205K tokens against 8K.

### How many benchmarks do GLM-5 and Llama 3-8B share?

22 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Llama 3-8B has 34.