Model comparison
GLM-4.5-Air vs Muse Spark 1.2
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 38.9 on the Noometry Index. GLM-4.5-Air costs 4.7× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
MetaSummary
- They share 14 benchmarks with published results for both. GLM-4.5-Air scores higher in 0 categories and Muse Spark 1.2 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 51.3 to 24.1.
- GLM-4.5-Air is cheaper at $0.20 / $1.10 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 131K.
- GLM-4.5-Air has downloadable open weights; the other is API-only.
Side by side
| GLM-4.5-Air | Muse Spark 1.2 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 38.9 | 50.3 |
| Released | 2025-07-20 | 2026-08-05 |
| Weights | Open | Proprietary |
| Context window | 131K | 1.05M |
| Max output | 98K | 131K |
| Input $ / M tokens | $0.20 | $1.25 |
| Output $ / M tokens | $1.10 | $4.25 |
| Results tracked | 27 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
GLM-4.5-Air: 33.3 (#259), Muse Spark 1.2: 49.2 (#51)
| Benchmark | GLM-4.5-Air | Muse Spark 1.2 |
|---|---|---|
| LMArena Coding | 1397 | 1495 |
| DeepSWE | — | 54.9% |
| LMArena WebDev | — | 1533 |
| FrontierSWE | — | 12% |
| SciCode | — | 56.4% |
| GSO | 2.9% | — |
| WeirdML | — | 60.3% |
Agentic & Tool Use Not comparable
GLM-4.5-Air: —, Muse Spark 1.2: 29.4 (#87)
| Benchmark | GLM-4.5-Air | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | — | 36.4% |
| GDP.pdf | — | 16% |
Reasoning Muse Spark 1.2 leads
GLM-4.5-Air: 24.1 (#166), Muse Spark 1.2: 51.3 (#34)
| Benchmark | GLM-4.5-Air | Muse Spark 1.2 |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1486 |
| SimpleBench | — | 74.5% |
| Kagi LLM Benchmark | 43% | — |
| NYT Connections (extended) | — | 79.2% |
| CritPt | — | 17.7% |
| DTBench | — | 94.7% |
| LMCA | — | 48.4% |
| Epoch Capabilities Index | — | 154.87 |
| ForecastBench | 59.2 | — |
Math Muse Spark 1.2 leads
GLM-4.5-Air: 36.2 (#170), Muse Spark 1.2: 46.4 (#70)
| Benchmark | GLM-4.5-Air | Muse Spark 1.2 |
|---|---|---|
| LMArena Math | 1396 | 1471 |
| ProofBench | — | 43% |
| Omni-MATH | 39.1% | — |
Knowledge Muse Spark 1.2 leads
GLM-4.5-Air: 35.0 (#191), Muse Spark 1.2: 54.1 (#53)
| Benchmark | GLM-4.5-Air | Muse Spark 1.2 |
|---|---|---|
| LMArena Expert | 1370 | 1480 |
| Humanity's Last Exam | 8.1% | — |
| SimpleQA Verified | — | 60.3% |
| MMLU-Pro | 76.2% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 59.4% | — |
Multimodal Not comparable
GLM-4.5-Air: —, Muse Spark 1.2: 43.4 (#25)
| Benchmark | GLM-4.5-Air | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | — | 1305 |
Multilingual Muse Spark 1.2 leads
GLM-4.5-Air: 49.1 (#135), Muse Spark 1.2: 57.1 (#11)
| Benchmark | GLM-4.5-Air | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1366 | 1478 |
| LMArena Chinese | 1426 | 1511 |
| LMArena French | 1399 | 1513 |
| LMArena Russian | 1373 | 1487 |
| LMArena Spanish | 1386 | 1498 |
| LMArena German | 1377 | — |
| LMArena Japanese | 1348 | — |
| LMArena Korean | 1308 | — |
Instruction Following Muse Spark 1.2 leads
GLM-4.5-Air: 69.6 (#171), Muse Spark 1.2: 76.7 (#36)
| Benchmark | GLM-4.5-Air | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1354 | 1461 |
| IFEval | 81.2% | — |
Long Context Muse Spark 1.2 leads
GLM-4.5-Air: 41.6 (#135), Muse Spark 1.2: 45.2 (#48)
| Benchmark | GLM-4.5-Air | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1366 | 1475 |
Writing & Preference Muse Spark 1.2 leads
GLM-4.5-Air: 55.9 (#139), Muse Spark 1.2: 72.3 (#14)
| Benchmark | GLM-4.5-Air | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1384 | 1482 |
| LMArena Creative Writing | 1343 | 1449 |
| LMArena Multi-Turn | 1371 | 1494 |
| EQ-Bench Creative Writing | — | 1840 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than Muse Spark 1.2?
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 38.9 on the Noometry Index. GLM-4.5-Air costs 4.7× 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-4.5-Air or Muse Spark 1.2?
GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.
Is GLM-4.5-Air or Muse Spark 1.2 better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 33.3 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.2 does, with 1.05M tokens against 131K.
How many benchmarks do GLM-4.5-Air and Muse Spark 1.2 share?
14 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Muse Spark 1.2 has 31.