Model comparison
GLM-5 vs Muse Spark 1.2
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 46.1 on the Noometry Index.
Last verified . 20 shared benchmarks.
MetaSummary
- They share 20 benchmarks with published results for both. GLM-5 scores higher in 1 category and Muse Spark 1.2 in 8 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 51.3 to 27.6.
- The biggest single-benchmark swing is SimpleBench: 53.2% for GLM-5 and 74.5% for Muse Spark 1.2.
- GLM-5 is cheaper at $1 / $3.20 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 205K.
- GLM-5 has downloadable open weights; the other is API-only.
Side by side
| GLM-5 | Muse Spark 1.2 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 46.1 | 50.3 |
| Released | 2026-02-11 | 2026-08-05 |
| Weights | Open | Proprietary |
| Context window | 205K | 1.05M |
| Max output | 131K | 131K |
| Input $ / M tokens | $1 | $1.25 |
| Output $ / M tokens | $3.20 | $4.25 |
| Results tracked | 45 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-5: 49.0 (#52), Muse Spark 1.2: 49.2 (#51)
| Benchmark | GLM-5 | Muse Spark 1.2 |
|---|---|---|
| LMArena WebDev | 1434 | 1533 |
| WeirdML | 48.2% | 60.3% |
| LMArena Coding | 1461 | 1495 |
| SWE-bench Verified | 72.1% | — |
| DeepSWE | — | 54.9% |
| SWE-bench Verified (bash only) | 72.8% | — |
| SWE-bench Multilingual | 69.7% | — |
| FrontierSWE | — | 12% |
| SciCode | — | 56.4% |
| ALE-Bench | 765.62 | — |
Agentic & Tool Use GLM-5 leads
GLM-5: 31.1 (#71), Muse Spark 1.2: 29.4 (#87)
| Benchmark | GLM-5 | Muse Spark 1.2 |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| APEX-Agents | — | 36.4% |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| GDP.pdf | — | 16% |
| Vending-Bench 2 | 4,432 | — |
Reasoning Muse Spark 1.2 leads
GLM-5: 27.6 (#116), Muse Spark 1.2: 51.3 (#34)
| Benchmark | GLM-5 | Muse Spark 1.2 |
|---|---|---|
| SimpleBench | 53.2% | 74.5% |
| NYT Connections (extended) | 74.8% | 79.2% |
| LMArena Hard Prompts | 1452 | 1486 |
| Epoch Capabilities Index | 145.83 | 154.87 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 75% | — |
| ARC-AGI-1 | 44.7% | — |
| CritPt | — | 17.7% |
| Chess Puzzles | 10% | — |
| DTBench | — | 94.7% |
| LMCA | — | 48.4% |
| ForecastBench | 61 | — |
Math Too close to call
GLM-5: 46.4 (#71), Muse Spark 1.2: 46.4 (#70)
| Benchmark | GLM-5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Math | 1440 | 1471 |
| MathArena Final-Answer Competitions | 65.7% | — |
| OTIS Mock AIME 2024-2025 | 80% | — |
| ProofBench | — | 43% |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Muse Spark 1.2 leads
GLM-5: 52.3 (#64), Muse Spark 1.2: 54.1 (#53)
| Benchmark | GLM-5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Expert | 1454 | 1480 |
| GPQA Diamond | 87.8% | — |
| SimpleQA Verified | — | 60.3% |
| Vectara Hallucination Rate | 10.1% | — |
Multimodal Not comparable
GLM-5: —, Muse Spark 1.2: 43.4 (#25)
| Benchmark | GLM-5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | — | 1305 |
Multilingual Muse Spark 1.2 leads
GLM-5: 53.7 (#58), Muse Spark 1.2: 57.1 (#11)
| Benchmark | GLM-5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1430 | 1478 |
| LMArena Chinese | 1511 | 1511 |
| LMArena French | 1455 | 1513 |
| LMArena Russian | 1436 | 1487 |
| LMArena Spanish | 1454 | 1498 |
| LMArena German | 1445 | — |
| LMArena Japanese | 1416 | — |
| LMArena Korean | 1423 | — |
Instruction Following Muse Spark 1.2 leads
GLM-5: 75.2 (#67), Muse Spark 1.2: 76.7 (#36)
| Benchmark | GLM-5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1428 | 1461 |
Long Context Too close to call
GLM-5: 44.7 (#60), Muse Spark 1.2: 45.2 (#48)
| Benchmark | GLM-5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1446 | 1475 |
| CL-bench | 18.7% | — |
Writing & Preference Muse Spark 1.2 leads
GLM-5: 66.0 (#38), Muse Spark 1.2: 72.3 (#14)
| Benchmark | GLM-5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1446 | 1482 |
| LMArena Creative Writing | 1439 | 1449 |
| EQ-Bench Creative Writing | 1601 | 1840 |
| LMArena Multi-Turn | 1456 | 1494 |
Frequently asked questions
Is GLM-5 better than Muse Spark 1.2?
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 46.1 on the Noometry Index.
Which is cheaper, GLM-5 or Muse Spark 1.2?
GLM-5 is cheaper. It lists at $1 per million input tokens and $3.20 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.
Is GLM-5 or Muse Spark 1.2 better for coding?
They score almost the same on coding (49.0 vs 49.2); test both on your own repository before choosing.
Which has the bigger context window?
Muse Spark 1.2 does, with 1.05M tokens against 205K.
How many benchmarks do GLM-5 and Muse Spark 1.2 share?
20 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Muse Spark 1.2 has 31.