Model comparison
GLM-4.5-Air vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.6 to 38.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
MetaSummary
- They share 17 benchmarks with published results for both. GLM-4.5-Air scores higher in 0 categories and Muse Spark in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 35.0.
- The biggest single-benchmark swing is Humanity's Last Exam: 8.1% for GLM-4.5-Air and 40.6% for Muse Spark.
- GLM-4.5-Air has downloadable open weights; the other is API-only.
Side by side
| GLM-4.5-Air | Muse Spark | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 38.9 | 50.6 |
| Released | 2025-07-20 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 98K | — |
| Input $ / M tokens | $0.20 | — |
| Output $ / M tokens | $1.10 | — |
| Results tracked | 27 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
GLM-4.5-Air: 33.3 (#259), Muse Spark: 46.2 (#69)
| Benchmark | GLM-4.5-Air | Muse Spark |
|---|---|---|
| LMArena Coding | 1397 | 1481 |
| SciCode | — | 51.5% |
| GSO | 2.9% | — |
Reasoning Muse Spark leads
GLM-4.5-Air: 24.1 (#166), Muse Spark: 35.9 (#67)
| Benchmark | GLM-4.5-Air | Muse Spark |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1474 |
| Kagi LLM Benchmark | 43% | — |
| CritPt | — | 11.3% |
| Epoch Capabilities Index | — | 152.04 |
| ForecastBench | 59.2 | — |
Math Muse Spark leads
GLM-4.5-Air: 36.2 (#170), Muse Spark: 47.8 (#66)
| Benchmark | GLM-4.5-Air | Muse Spark |
|---|---|---|
| LMArena Math | 1396 | 1455 |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 17% |
| Omni-MATH | 39.1% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Muse Spark leads
GLM-4.5-Air: 35.0 (#191), Muse Spark: 65.7 (#13)
| Benchmark | GLM-4.5-Air | Muse Spark |
|---|---|---|
| Humanity's Last Exam | 8.1% | 40.6% |
| LMArena Expert | 1370 | 1457 |
| GPQA Diamond | — | 89.8% |
| MMLU-Pro | 76.2% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 59.4% | — |
Multimodal Not comparable
GLM-4.5-Air: —, Muse Spark: 43.4 (#24)
| Benchmark | GLM-4.5-Air | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Muse Spark leads
GLM-4.5-Air: 49.1 (#135), Muse Spark: 56.1 (#24)
| Benchmark | GLM-4.5-Air | Muse Spark |
|---|---|---|
| LMArena Non-English | 1366 | 1464 |
| LMArena Chinese | 1426 | 1509 |
| LMArena French | 1399 | 1497 |
| LMArena German | 1377 | 1497 |
| LMArena Korean | 1308 | 1459 |
| LMArena Russian | 1373 | 1466 |
| LMArena Spanish | 1386 | 1472 |
| LMArena Japanese | 1348 | — |
Instruction Following Muse Spark leads
GLM-4.5-Air: 69.6 (#171), Muse Spark: 75.9 (#51)
| Benchmark | GLM-4.5-Air | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1354 | 1442 |
| IFEval | 81.2% | — |
Long Context Muse Spark leads
GLM-4.5-Air: 41.6 (#135), Muse Spark: 44.4 (#69)
| Benchmark | GLM-4.5-Air | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1366 | 1451 |
Writing & Preference Muse Spark leads
GLM-4.5-Air: 55.9 (#139), Muse Spark: 66.0 (#39)
| Benchmark | GLM-4.5-Air | Muse Spark |
|---|---|---|
| LMArena Text | 1384 | 1474 |
| LMArena Creative Writing | 1343 | 1459 |
| LMArena Multi-Turn | 1371 | 1477 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.6 to 38.9 on the Noometry Index.
Is GLM-4.5-Air or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 33.3 in the Noometry coding category.
How many benchmarks do GLM-4.5-Air and Muse Spark share?
17 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Muse Spark has 27.