# GLM-5.1 vs Muse Spark

> Muse Spark is the stronger model overall, scoring 50.6 to 47.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-muse-spark
- Last updated: 2026-10-11
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. GLM-5.1 scores higher in 6 categories and Muse Spark in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 54.9.
- The biggest single-benchmark swing is SciCode: 43.8% for GLM-5.1 and 51.5% for Muse Spark.
- GLM-5.1 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-5.1 | Muse Spark |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 47.8 | 50.6 |
| Rank | 59 | 46 |
| Context | 200K | — |
| Input $/M | $1.40 | — |
| Output $/M | $4.40 | — |
| Weights | Open | Proprietary |

## Coding

- GLM-5.1: 48.7 (#55)
- Muse Spark: 46.2 (#69)

| Benchmark | GLM-5.1 | Muse Spark |
|---|---|---|
| SciCode | 43.8% | 51.5% |
| LMArena Coding | 1485 | 1481 |
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1508 | — |
| WeirdML | 57.1% | — |
| ALE-Bench | 887.1 | — |

## Agentic & Tool Use

- GLM-5.1: 24.9 (#113)
- Muse Spark: —

| Benchmark | GLM-5.1 | Muse Spark |
|---|---|---|
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 39.1 (#60)
- Muse Spark: 35.9 (#67)

| Benchmark | GLM-5.1 | Muse Spark |
|---|---|---|
| CritPt | 4.6% | 11.3% |
| LMArena Hard Prompts | 1472 | 1474 |
| Epoch Capabilities Index | 149.84 | 152.04 |
| SimpleBench | 55.1% | — |
| NYT Connections (extended) | 77.7% | — |
| Chess Puzzles | 19% | — |
| Thematic Generalization | 69.8% | — |

## Math

- GLM-5.1: 49.7 (#60)
- Muse Spark: 47.8 (#66)

| Benchmark | GLM-5.1 | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 88.9% |
| ProofBench | 22.2% | 17% |
| LMArena Math | 1473 | 1455 |
| FrontierMath (Feb 2025 set) | 33.4% | 39% |
| FrontierMath Tier 4 (v1) | 12.5% | 14.6% |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |

## Knowledge

- GLM-5.1: 54.9 (#50)
- Muse Spark: 65.7 (#13)

| Benchmark | GLM-5.1 | Muse Spark |
|---|---|---|
| GPQA Diamond | 89.9% | 89.8% |
| LMArena Expert | 1476 | 1457 |
| Humanity's Last Exam | — | 40.6% |
| SimpleQA Verified | 34% | — |

## Multimodal

- GLM-5.1: —
- Muse Spark: 43.4 (#24)

| Benchmark | GLM-5.1 | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |

## Multilingual

- GLM-5.1: 55.0 (#36)
- Muse Spark: 56.1 (#24)

| Benchmark | GLM-5.1 | Muse Spark |
|---|---|---|
| LMArena Non-English | 1447 | 1464 |
| LMArena Chinese | 1515 | 1509 |
| LMArena French | 1474 | 1497 |
| LMArena German | 1465 | 1497 |
| LMArena Korean | 1418 | 1459 |
| LMArena Russian | 1454 | 1466 |
| LMArena Spanish | 1469 | 1472 |
| LMArena Japanese | 1434 | — |

## Instruction Following

- GLM-5.1: 76.3 (#42)
- Muse Spark: 75.9 (#51)

| Benchmark | GLM-5.1 | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1451 | 1442 |

## Long Context

- GLM-5.1: 44.9 (#53)
- Muse Spark: 44.4 (#69)

| Benchmark | GLM-5.1 | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1466 | 1451 |

## Writing & Preference

- GLM-5.1: 66.9 (#31)
- Muse Spark: 66.0 (#39)

| Benchmark | GLM-5.1 | Muse Spark |
|---|---|---|
| LMArena Text | 1461 | 1474 |
| LMArena Creative Writing | 1453 | 1459 |
| LMArena Multi-Turn | 1472 | 1477 |
| EQ-Bench Creative Writing | 1592 | — |

## FAQ

### Is GLM-5.1 better than Muse Spark?

Muse Spark is the stronger model overall, scoring 50.6 to 47.8 on the Noometry Index.

### Is GLM-5.1 or Muse Spark better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.7 versus 46.2 in the Noometry coding category.

### How many benchmarks do GLM-5.1 and Muse Spark share?

24 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Muse Spark has 27.