# GLM-4.7 vs Llama 3.2 1B

> GLM-4.7 is the stronger model overall, scoring 41.7 to 19.9 on the Noometry Index. Llama 3.2 1B costs 14× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-4-7-vs-llama-3-2-1b
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. GLM-4.7 scores higher in 9 categories and Llama 3.2 1B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.7 leads 47.0 to 7.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.3% for GLM-4.7 and 0.6% for Llama 3.2 1B.
- Llama 3.2 1B is cheaper at $0.027 / $0.20 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
- GLM-4.7 accepts more context: 205K tokens versus 60K.

## Snapshot

| | GLM-4.7 | Llama 3.2 1B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 41.7 | 19.9 |
| Rank | 117 | 349 |
| Context | 205K | 60K |
| Input $/M | $0.60 | $0.027 |
| Output $/M | $2.20 | $0.20 |
| Weights | Open | Open |

## Coding

- GLM-4.7: 43.6 (#74)
- Llama 3.2 1B: 20.6 (#333)

| Benchmark | GLM-4.7 | Llama 3.2 1B |
|---|---|---|
| LMArena Coding | 1454 | 1071 |
| LMArena WebDev | 1435 | — |
| SciCode | 45.1% | — |
| BigCodeBench Instruct | — | 8.2% |
| BigCodeBench Complete | — | 11.3% |
| ALE-Bench | 399.48 | — |

## Agentic & Tool Use

- GLM-4.7: 26.4 (#96)
- Llama 3.2 1B: 14.5 (#142)

| Benchmark | GLM-4.7 | Llama 3.2 1B |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| Berkeley Function Calling Leaderboard | — | 10.8% |
| BALROG | — | 6.6% |
| Vending-Bench 2 | 2,377 | — |

## Reasoning

- GLM-4.7: 23.7 (#161)
- Llama 3.2 1B: 15.6 (#304)

| Benchmark | GLM-4.7 | Llama 3.2 1B |
|---|---|---|
| Chess Puzzles | 6% | 0% |
| LMArena Hard Prompts | 1443 | 1044 |
| Epoch Capabilities Index | 143.53 | 101.95 |
| SimpleBench | 47.7% | — |
| CritPt | 1.7% | — |

## Math

- GLM-4.7: 37.7 (#92)
- Llama 3.2 1B: 9.7 (#308)

| Benchmark | GLM-4.7 | Llama 3.2 1B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 0.6% |
| LMArena Math | 1423 | 1086 |
| ProofBench | 6% | — |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- GLM-4.7: 47.0 (#74)
- Llama 3.2 1B: 7.2 (#307)

| Benchmark | GLM-4.7 | Llama 3.2 1B |
|---|---|---|
| GPQA Diamond | 83.3% | 23.9% |
| LMArena Expert | 1424 | 1007 |
| SimpleQA Verified | 32.2% | — |
| Vectara Hallucination Rate | 11.7% | — |

## Multilingual

- GLM-4.7: 53.0 (#75)
- Llama 3.2 1B: 23.9 (#287)

| Benchmark | GLM-4.7 | Llama 3.2 1B |
|---|---|---|
| LMArena Non-English | 1417 | 973 |
| LMArena Chinese | 1495 | 958 |
| LMArena German | 1426 | 1014 |
| LMArena Russian | 1423 | 941 |
| LMArena French | 1432 | — |
| LMArena Japanese | 1439 | — |
| LMArena Korean | 1401 | — |
| LMArena Spanish | 1433 | — |

## Instruction Following

- GLM-4.7: 74.6 (#90)
- Llama 3.2 1B: 52.6 (#285)

| Benchmark | GLM-4.7 | Llama 3.2 1B |
|---|---|---|
| LMArena Instruction Following | 1411 | 1031 |

## Long Context

- GLM-4.7: 42.8 (#111)
- Llama 3.2 1B: 31.9 (#269)

| Benchmark | GLM-4.7 | Llama 3.2 1B |
|---|---|---|
| LMArena Longer Query | 1432 | 1050 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |

## Writing & Preference

- GLM-4.7: 61.1 (#89)
- Llama 3.2 1B: 21.4 (#305)

| Benchmark | GLM-4.7 | Llama 3.2 1B |
|---|---|---|
| LMArena Text | 1436 | 1055 |
| LMArena Creative Writing | 1401 | 1033 |
| EQ-Bench Creative Writing | 1413 | 200 |
| LMArena Multi-Turn | 1446 | 1030 |

## FAQ

### Is GLM-4.7 better than Llama 3.2 1B?

GLM-4.7 is the stronger model overall, scoring 41.7 to 19.9 on the Noometry Index. Llama 3.2 1B costs 14× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.

### Which is cheaper, GLM-4.7 or Llama 3.2 1B?

Llama 3.2 1B is cheaper. It lists at $0.027 per million input tokens and $0.20 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.

### Is GLM-4.7 or Llama 3.2 1B better for coding?

GLM-4.7 scores higher on coding benchmarks: 43.6 versus 20.6 in the Noometry coding category.

### Which has the bigger context window?

GLM-4.7 does, with 205K tokens against 60K.

### How many benchmarks do GLM-4.7 and Llama 3.2 1B share?

18 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Llama 3.2 1B has 22.