# GLM-4.7 vs Muse Spark 1.2

> Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 41.7 on the Noometry Index. GLM-4.7 costs 2.0× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-4-7-vs-muse-spark-1-2
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. GLM-4.7 scores higher in 0 categories and Muse Spark 1.2 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 50.4 to 23.7.
- The biggest single-benchmark swing is ProofBench: 6% for GLM-4.7 and 43% for Muse Spark 1.2.
- GLM-4.7 is cheaper at $0.60 / $2.20 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.2.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 205K.
- GLM-4.7 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-4.7 | Muse Spark 1.2 |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 41.7 | 49.8 |
| Rank | 117 | 44 |
| Context | 205K | 1.05M |
| Input $/M | $0.60 | $1.25 |
| Output $/M | $2.20 | $4.25 |
| Weights | Open | Proprietary |

## Coding

- GLM-4.7: 43.6 (#74)
- Muse Spark 1.2: 48.6 (#49)

| Benchmark | GLM-4.7 | Muse Spark 1.2 |
|---|---|---|
| LMArena WebDev | 1435 | 1532 |
| SciCode | 45.1% | 56.4% |
| LMArena Coding | 1454 | 1497 |
| DeepSWE | — | 54.9% |
| FrontierSWE | — | 12% |
| WeirdML | — | 60.3% |
| ALE-Bench | 399.48 | — |

## Agentic & Tool Use

- GLM-4.7: 26.4 (#96)
- Muse Spark 1.2: 29.5 (#77)

| Benchmark | GLM-4.7 | Muse Spark 1.2 |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| APEX-Agents | — | 36.4% |
| GDP.pdf | — | 16% |
| Vending-Bench 2 | 2,377 | — |

## Reasoning

- GLM-4.7: 23.7 (#161)
- Muse Spark 1.2: 50.4 (#32)

| Benchmark | GLM-4.7 | Muse Spark 1.2 |
|---|---|---|
| SimpleBench | 47.7% | 74.5% |
| CritPt | 1.7% | 17.7% |
| LMArena Hard Prompts | 1443 | 1490 |
| Epoch Capabilities Index | 143.53 | 155.18 |
| NYT Connections (extended) | — | 79.2% |
| Chess Puzzles | 6% | — |
| DTBench | — | 94.7% |
| LMCA | — | 48.4% |

## Math

- GLM-4.7: 37.7 (#92)
- Muse Spark 1.2: 43.8 (#68)

| Benchmark | GLM-4.7 | Muse Spark 1.2 |
|---|---|---|
| ProofBench | 6% | 43% |
| OTIS Mock AIME 2024-2025 | 83.3% | — |
| LMArena Math | 1423 | — |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- GLM-4.7: 47.0 (#74)
- Muse Spark 1.2: 53.9 (#49)

| Benchmark | GLM-4.7 | Muse Spark 1.2 |
|---|---|---|
| SimpleQA Verified | 32.2% | 60.3% |
| LMArena Expert | 1424 | 1485 |
| GPQA Diamond | 83.3% | — |
| Vectara Hallucination Rate | 11.7% | — |

## Multimodal

- GLM-4.7: —
- Muse Spark 1.2: 42.6 (#24)

| Benchmark | GLM-4.7 | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | — | 1304 |

## Multilingual

- GLM-4.7: 53.0 (#75)
- Muse Spark 1.2: 57.4 (#10)

| Benchmark | GLM-4.7 | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1417 | 1479 |
| LMArena Chinese | 1495 | 1519 |
| LMArena Russian | 1423 | 1494 |
| LMArena French | 1432 | — |
| LMArena German | 1426 | — |
| LMArena Japanese | 1439 | — |
| LMArena Korean | 1401 | — |
| LMArena Spanish | 1433 | — |

## Instruction Following

- GLM-4.7: 74.6 (#90)
- Muse Spark 1.2: 77.1 (#30)

| Benchmark | GLM-4.7 | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1411 | 1466 |

## Long Context

- GLM-4.7: 42.8 (#111)
- Muse Spark 1.2: 45.4 (#35)

| Benchmark | GLM-4.7 | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1432 | 1483 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |

## Writing & Preference

- GLM-4.7: 61.1 (#89)
- Muse Spark 1.2: 72.6 (#14)

| Benchmark | GLM-4.7 | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1436 | 1486 |
| LMArena Creative Writing | 1401 | 1444 |
| EQ-Bench Creative Writing | 1413 | 1840 |
| LMArena Multi-Turn | 1446 | 1504 |

## FAQ

### Is GLM-4.7 better than Muse Spark 1.2?

Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 41.7 on the Noometry Index. GLM-4.7 costs 2.0× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.

### Which is cheaper, GLM-4.7 or Muse Spark 1.2?

GLM-4.7 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.

### Is GLM-4.7 or Muse Spark 1.2 better for coding?

Muse Spark 1.2 scores higher on coding benchmarks: 48.6 versus 43.6 in the Noometry coding category.

### Which has the bigger context window?

Muse Spark 1.2 does, with 1.05M tokens against 205K.

### How many benchmarks do GLM-4.7 and Muse Spark 1.2 share?

19 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Muse Spark 1.2 has 28.