Model comparison
GLM-5.2 vs Muse Spark 1.1
GLM-5.2 is the stronger model overall, scoring 50.9 to 49.9 on the Noometry Index.
Last verified . 33 shared benchmarks.
MetaSummary
- They share 33 benchmarks with published results for both. GLM-5.2 scores higher in 5 categories and Muse Spark 1.1 in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.2 leads 55.4 to 44.0.
- The biggest single-benchmark swing is SimpleQA Verified: 34.2% for GLM-5.2 and 57.8% for Muse Spark 1.1.
- Muse Spark 1.1 is cheaper at $1.25 / $4.25 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
- Muse Spark 1.1 accepts more context: 1.05M tokens versus 1M.
- GLM-5.2 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.2 | Muse Spark 1.1 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 50.9 | 49.9 |
| Released | 2026-06-13 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 131K | 131K |
| Input $ / M tokens | $1.40 | $1.25 |
| Output $ / M tokens | $4.40 | $4.25 |
| Results tracked | 50 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-5.2: 50.9 (#37), Muse Spark 1.1: 50.8 (#38)
| Benchmark | GLM-5.2 | Muse Spark 1.1 |
|---|---|---|
| DeepSWE | 43.8% | 53.3% |
| LMArena WebDev | 1604 | 1542 |
| SciCode | 50.5% | 58.8% |
| LMArena Coding | 1484 | 1497 |
| SWE-bench Verified | 78.7% | — |
| FrontierCode | 24.5% | — |
| WeirdML | 70.1% | — |
| ALE-Bench | 1,047 | — |
Agentic & Tool Use Muse Spark 1.1 leads
GLM-5.2: 31.6 (#63), Muse Spark 1.1: 33.9 (#45)
| Benchmark | GLM-5.2 | Muse Spark 1.1 |
|---|---|---|
| τ²-bench Banking | 37.1% | 40.5% |
| GBAEval | 0% | 7.9% |
| Vending-Bench 2 | 8,314 | 6,520 |
| PostTrainBench | 31.7% | — |
| GDP.pdf | — | 15% |
Reasoning Muse Spark 1.1 leads
GLM-5.2: 42.1 (#46), Muse Spark 1.1: 45.9 (#41)
| Benchmark | GLM-5.2 | Muse Spark 1.1 |
|---|---|---|
| NYT Connections (extended) | 74.3% | 84.9% |
| CritPt | 20.9% | 15.1% |
| LMArena Hard Prompts | 1480 | 1486 |
| DTBench | 93.6% | 94.4% |
| LMCA | 45.8% | 49.9% |
| Surface Evolver Bench | 55.6% | 52.5% |
| Epoch Capabilities Index | 151.76 | 154.32 |
| ARC-AGI-2 | 22.8% | — |
| SimpleBench | 58.8% | — |
| Kagi LLM Benchmark | 62.6% | — |
| ARC-AGI-1 | 77% | — |
| Chess Puzzles | 21% | — |
| EBR-Bench | 9.5% | — |
| Mystery Game Puzzles | 19% | — |
Math GLM-5.2 leads
GLM-5.2: 55.4 (#35), Muse Spark 1.1: 44.0 (#67)
| Benchmark | GLM-5.2 | Muse Spark 1.1 |
|---|---|---|
| ProofBench | 35% | 39% |
| LMArena Math | 1482 | 1477 |
| FrontierMath (Tiers 1-3) | 59.2% | — |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| OTIS Mock AIME 2024-2025 | 86.4% | — |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#36), Muse Spark 1.1: 52.8 (#55)
| Benchmark | GLM-5.2 | Muse Spark 1.1 |
|---|---|---|
| SimpleQA Verified | 34.2% | 57.8% |
| LMArena Expert | 1484 | 1480 |
| GPQA Diamond | 91.9% | — |
Multimodal Not comparable
GLM-5.2: —, Muse Spark 1.1: 41.9 (#28)
| Benchmark | GLM-5.2 | Muse Spark 1.1 |
|---|---|---|
| LMArena Vision | — | 1292 |
| LMArena Document | — | 1465 |
Multilingual Too close to call
GLM-5.2: 56.0 (#25), Muse Spark 1.1: 56.8 (#16)
| Benchmark | GLM-5.2 | Muse Spark 1.1 |
|---|---|---|
| LMArena Non-English | 1459 | 1471 |
| LMArena Chinese | 1518 | 1518 |
| LMArena French | 1476 | 1494 |
| LMArena German | 1470 | 1466 |
| LMArena Japanese | 1451 | 1445 |
| LMArena Korean | 1445 | 1459 |
| LMArena Russian | 1467 | 1482 |
| LMArena Spanish | 1477 | 1471 |
Instruction Following Too close to call
GLM-5.2: 77.1 (#32), Muse Spark 1.1: 76.8 (#36)
| Benchmark | GLM-5.2 | Muse Spark 1.1 |
|---|---|---|
| LMArena Instruction Following | 1465 | 1457 |
Long Context Too close to call
GLM-5.2: 45.3 (#43), Muse Spark 1.1: 44.8 (#55)
| Benchmark | GLM-5.2 | Muse Spark 1.1 |
|---|---|---|
| LMArena Longer Query | 1479 | 1463 |
Writing & Preference Muse Spark 1.1 leads
GLM-5.2: 70.7 (#20), Muse Spark 1.1: 73.6 (#11)
| Benchmark | GLM-5.2 | Muse Spark 1.1 |
|---|---|---|
| LMArena Text | 1470 | 1479 |
| LMArena Creative Writing | 1465 | 1440 |
| EQ-Bench Creative Writing | 1757 | 1927 |
| EQ-Bench 4 | 1222 | 1260 |
| LMArena Multi-Turn | 1468 | 1484 |
Frequently asked questions
Is GLM-5.2 better than Muse Spark 1.1?
GLM-5.2 is the stronger model overall, scoring 50.9 to 49.9 on the Noometry Index.
Which is cheaper, GLM-5.2 or Muse Spark 1.1?
Muse Spark 1.1 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; GLM-5.2 lists at $1.40 and $4.40.
Is GLM-5.2 or Muse Spark 1.1 better for coding?
They score almost the same on coding (50.9 vs 50.8); test both on your own repository before choosing.
Which has the bigger context window?
Muse Spark 1.1 does, with 1.05M tokens against 1M.
How many benchmarks do GLM-5.2 and Muse Spark 1.1 share?
33 benchmarks have published results for both models. GLM-5.2 has 50 scored results on Noometry and Muse Spark 1.1 has 36.