Model comparison
GLM-5.2 vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 51.1 on the Noometry Index.
Last verified . 32 shared benchmarks.
MetaSummary
- They share 32 benchmarks with published results for both. GLM-5.2 scores higher in 1 category and Muse Spark 1.3 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 55.7.
- The biggest single-benchmark swing is ProofBench: 35% for GLM-5.2 and 58% for Muse Spark 1.3.
- Muse Spark 1.3 is cheaper at $1.25 / $4.25 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
- Muse Spark 1.3 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 1.3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 51.1 | 54.8 |
| Released | 2026-06-13 | 2026-09-02 |
| 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 | 51 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
GLM-5.2: 51.3 (#41), Muse Spark 1.3: 56.6 (#21)
| Benchmark | GLM-5.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena WebDev | 1603 | 1657 |
| SciCode | 50.5% | 59.7% |
| LMArena Coding | 1485 | 1514 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| CursorBench | — | 41.6% |
| WeirdML | 70.1% | — |
| ALE-Bench | 1,047 | — |
Agentic & Tool Use Muse Spark 1.3 leads
GLM-5.2: 32.4 (#63), Muse Spark 1.3: 38.6 (#30)
| Benchmark | GLM-5.2 | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | 45.2% | 57.8% |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| GDP.pdf | — | 27.6% |
| Vending-Bench 2 | 8,314 | — |
Reasoning Muse Spark 1.3 leads
GLM-5.2: 42.3 (#52), Muse Spark 1.3: 54.0 (#27)
| Benchmark | GLM-5.2 | Muse Spark 1.3 |
|---|---|---|
| NYT Connections (extended) | 74.3% | 85.1% |
| CritPt | 20.9% | 26% |
| Chess Puzzles | 21% | 38% |
| LMArena Hard Prompts | 1480 | 1503 |
| Mystery Game Puzzles | 19% | 25% |
| DTBench | 93.6% | 96.5% |
| LMCA | 45.8% | 53.9% |
| Epoch Capabilities Index | 151.78 | 156.75 |
| ARC-AGI-2 | 22.8% | — |
| SimpleBench | 58.8% | — |
| Kagi LLM Benchmark | 62.6% | — |
| ARC-AGI-1 | 77% | — |
| EBR-Bench | 9.5% | — |
| Surface Evolver Bench | 55.6% | — |
| Bench to the Future 3 | — | 0.14 |
Math Muse Spark 1.3 leads
GLM-5.2: 55.7 (#43), Muse Spark 1.3: 73.1 (#21)
| Benchmark | GLM-5.2 | Muse Spark 1.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 59.2% | 74.4% |
| FrontierMath Tier 4 | 29.3% | 46.3% |
| OTIS Mock AIME 2024-2025 | 86.4% | 99.2% |
| ProofBench | 35% | 58% |
| LMArena Math | 1482 | 1494 |
| MathArena Final-Answer Competitions | 67.6% | — |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#40), Muse Spark 1.3: 42.6 (#95)
| Benchmark | GLM-5.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1486 | 1516 |
| GPQA Diamond | 91.9% | — |
| SimpleQA Verified | 34.2% | — |
Multimodal Not comparable
GLM-5.2: —, Muse Spark 1.3: 43.7 (#22)
| Benchmark | GLM-5.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | — | 1309 |
| LMArena Document | — | 1471 |
Multilingual Muse Spark 1.3 leads
GLM-5.2: 55.8 (#26), Muse Spark 1.3: 57.4 (#8)
| Benchmark | GLM-5.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1459 | 1481 |
| LMArena Chinese | 1519 | 1529 |
| LMArena French | 1479 | 1524 |
| LMArena German | 1468 | 1515 |
| LMArena Japanese | 1451 | 1474 |
| LMArena Korean | 1445 | 1501 |
| LMArena Russian | 1466 | 1490 |
| LMArena Spanish | 1477 | 1490 |
Instruction Following Too close to call
GLM-5.2: 76.9 (#34), Muse Spark 1.3: 77.5 (#22)
| Benchmark | GLM-5.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1465 | 1477 |
Long Context Too close to call
GLM-5.2: 45.3 (#43), Muse Spark 1.3: 45.6 (#32)
| Benchmark | GLM-5.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1479 | 1488 |
Writing & Preference Muse Spark 1.3 leads
GLM-5.2: 70.4 (#21), Muse Spark 1.3: 73.6 (#9)
| Benchmark | GLM-5.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1470 | 1490 |
| LMArena Creative Writing | 1462 | 1455 |
| EQ-Bench Creative Writing | 1757 | 1906 |
| LMArena Multi-Turn | 1469 | 1482 |
| EQ-Bench 4 | 1222 | — |
Frequently asked questions
Is GLM-5.2 better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 51.1 on the Noometry Index.
Which is cheaper, GLM-5.2 or Muse Spark 1.3?
Muse Spark 1.3 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 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 51.3 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.3 does, with 1.05M tokens against 1M.
How many benchmarks do GLM-5.2 and Muse Spark 1.3 share?
32 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and Muse Spark 1.3 has 37.