# GLM-4.7 vs Llama 4 Scout

> GLM-4.7 is the stronger model overall, scoring 41.7 to 27.4 on the Noometry Index. Llama 4 Scout costs 6.7× 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-4-scout
- Last updated: 2026-10-10
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. GLM-4.7 scores higher in 9 categories and Llama 4 Scout in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.7 leads 61.1 to 37.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.3% for GLM-4.7 and 7.8% for Llama 4 Scout.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
- GLM-4.7 accepts more context: 205K tokens versus 128K.

## Snapshot

| | GLM-4.7 | Llama 4 Scout |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 41.7 | 27.4 |
| Rank | 117 | 323 |
| Context | 205K | 128K |
| Input $/M | $0.60 | $0.10 |
| Output $/M | $2.20 | $0.30 |
| Weights | Open | Open |

## Coding

- GLM-4.7: 43.6 (#74)
- Llama 4 Scout: 19.9 (#334)

| Benchmark | GLM-4.7 | Llama 4 Scout |
|---|---|---|
| SciCode | 45.1% | 17% |
| LMArena Coding | 1454 | 1286 |
| SWE-bench Verified (bash only) | — | 9.1% |
| LMArena WebDev | 1435 | — |
| BigCodeBench Complete | — | 43.1% |
| ALE-Bench | 399.48 | — |

## Agentic & Tool Use

- GLM-4.7: 26.4 (#96)
- Llama 4 Scout: 24.4 (#109)

| Benchmark | GLM-4.7 | Llama 4 Scout |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| Berkeley Function Calling Leaderboard | — | 28.1% |
| Vending-Bench 2 | 2,377 | — |

## Reasoning

- GLM-4.7: 23.7 (#161)
- Llama 4 Scout: 9.2 (#339)

| Benchmark | GLM-4.7 | Llama 4 Scout |
|---|---|---|
| CritPt | 1.7% | 0% |
| LMArena Hard Prompts | 1443 | 1266 |
| Epoch Capabilities Index | 143.53 | 129.64 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | 47.7% | — |
| Kagi LLM Benchmark | — | 36.9% |
| ARC-AGI-1 | — | 0.5% |
| Chess Puzzles | 6% | — |
| DTBench | — | 57.9% |
| LMCA | — | 12% |
| ForecastBench | — | 57.5 |

## Math

- GLM-4.7: 37.7 (#92)
- Llama 4 Scout: 18.4 (#280)

| Benchmark | GLM-4.7 | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 7.8% |
| LMArena Math | 1423 | 1286 |
| FrontierMath (Feb 2025 set) | 2.4% | 0% |
| ProofBench | 6% | — |
| Omni-MATH | — | 37.3% |
| MATH Level 5 | — | 62.3% |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- GLM-4.7: 47.0 (#74)
- Llama 4 Scout: 31.8 (#208)

| Benchmark | GLM-4.7 | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | 83.3% | 51.8% |
| Vectara Hallucination Rate | 11.7% | 7.7% |
| LMArena Expert | 1424 | 1236 |
| SimpleQA Verified | 32.2% | — |
| MMLU-Pro | — | 74.2% |
| GPQA (HELM) | — | 50.7% |

## Multimodal

- GLM-4.7: —
- Llama 4 Scout: 31.6 (#98)

| Benchmark | GLM-4.7 | Llama 4 Scout |
|---|---|---|
| LMArena Vision | — | 1118 |
| SpatialViz-Bench | — | 34.2% |

## Multilingual

- GLM-4.7: 53.0 (#75)
- Llama 4 Scout: 41.3 (#207)

| Benchmark | GLM-4.7 | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1417 | 1253 |
| LMArena Chinese | 1495 | 1256 |
| LMArena French | 1432 | 1283 |
| LMArena German | 1426 | 1274 |
| LMArena Japanese | 1439 | 1209 |
| LMArena Korean | 1401 | 1207 |
| LMArena Russian | 1423 | 1263 |
| LMArena Spanish | 1433 | 1277 |

## Instruction Following

- GLM-4.7: 74.6 (#90)
- Llama 4 Scout: 66.0 (#212)

| Benchmark | GLM-4.7 | Llama 4 Scout |
|---|---|---|
| LMArena Instruction Following | 1411 | 1248 |
| IFEval | — | 81.8% |

## Long Context

- GLM-4.7: 42.8 (#111)
- Llama 4 Scout: 27.5 (#289)

| Benchmark | GLM-4.7 | Llama 4 Scout |
|---|---|---|
| LMArena Longer Query | 1432 | 1265 |
| Fiction.LiveBench | — | 36% |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |

## Writing & Preference

- GLM-4.7: 61.1 (#89)
- Llama 4 Scout: 37.1 (#256)

| Benchmark | GLM-4.7 | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1436 | 1279 |
| LMArena Creative Writing | 1401 | 1249 |
| EQ-Bench Creative Writing | 1413 | 783 |
| LMArena Multi-Turn | 1446 | 1281 |
| WildBench | — | 78% |

## FAQ

### Is GLM-4.7 better than Llama 4 Scout?

GLM-4.7 is the stronger model overall, scoring 41.7 to 27.4 on the Noometry Index. Llama 4 Scout costs 6.7× 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 4 Scout?

Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.

### Is GLM-4.7 or Llama 4 Scout better for coding?

GLM-4.7 scores higher on coding benchmarks: 43.6 versus 19.9 in the Noometry coding category.

### Which has the bigger context window?

GLM-4.7 does, with 205K tokens against 128K.

### How many benchmarks do GLM-4.7 and Llama 4 Scout share?

25 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Llama 4 Scout has 43.