Model comparison
GLM-4.6 vs Muse Spark 1.2
Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 40.9 on the Noometry Index. GLM-4.6 costs 2.0× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
MetaSummary
- They share 15 benchmarks with published results for both. GLM-4.6 scores higher in 1 category and Muse Spark 1.2 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 50.4 to 23.1.
- The biggest single-benchmark swing is SciCode: 38.4% for GLM-4.6 and 56.4% for Muse Spark 1.2.
- GLM-4.6 is cheaper at $0.60 / $2.20 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-4.6 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6 | Muse Spark 1.2 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 40.9 | 49.8 |
| Released | 2025-09-30 | 2026-08-05 |
| Weights | Open | Proprietary |
| Context window | 205K | 1.05M |
| Max output | 131K | 131K |
| Input $ / M tokens | $0.60 | $1.25 |
| Output $ / M tokens | $2.20 | $4.25 |
| Results tracked | 29 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
GLM-4.6: 39.9 (#137), Muse Spark 1.2: 48.6 (#49)
| Benchmark | GLM-4.6 | Muse Spark 1.2 |
|---|---|---|
| LMArena WebDev | 1339 | 1532 |
| SciCode | 38.4% | 56.4% |
| LMArena Coding | 1449 | 1497 |
| DeepSWE | — | 54.9% |
| SWE-bench Verified (bash only) | 55.4% | — |
| FrontierSWE | — | 12% |
| WeirdML | — | 60.3% |
| ALE-Bench | 340.82 | — |
Agentic & Tool Use GLM-4.6 leads
GLM-4.6: 32.1 (#60), Muse Spark 1.2: 29.5 (#77)
| Benchmark | GLM-4.6 | Muse Spark 1.2 |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| APEX-Agents | — | 36.4% |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| GDP.pdf | — | 16% |
Reasoning Muse Spark 1.2 leads
GLM-4.6: 23.1 (#168), Muse Spark 1.2: 50.4 (#32)
| Benchmark | GLM-4.6 | Muse Spark 1.2 |
|---|---|---|
| CritPt | 1.1% | 17.7% |
| LMArena Hard Prompts | 1440 | 1490 |
| SimpleBench | — | 74.5% |
| Kagi LLM Benchmark | 47.4% | — |
| NYT Connections (extended) | — | 79.2% |
| DTBench | — | 94.7% |
| LMCA | — | 48.4% |
| Epoch Capabilities Index | — | 155.18 |
Math Muse Spark 1.2 leads
GLM-4.6: 36.4 (#115), Muse Spark 1.2: 43.8 (#68)
| Benchmark | GLM-4.6 | Muse Spark 1.2 |
|---|---|---|
| ProofBench | — | 43% |
| LMArena Math | 1431 | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Muse Spark 1.2 leads
GLM-4.6: 39.6 (#118), Muse Spark 1.2: 53.9 (#49)
| Benchmark | GLM-4.6 | Muse Spark 1.2 |
|---|---|---|
| LMArena Expert | 1432 | 1485 |
| SimpleQA Verified | — | 60.3% |
| Vectara Hallucination Rate | 9.5% | — |
Multimodal Not comparable
GLM-4.6: —, Muse Spark 1.2: 42.6 (#24)
| Benchmark | GLM-4.6 | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | — | 1304 |
Multilingual Muse Spark 1.2 leads
GLM-4.6: 53.6 (#62), Muse Spark 1.2: 57.4 (#10)
| Benchmark | GLM-4.6 | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1426 | 1479 |
| LMArena Chinese | 1500 | 1519 |
| LMArena Russian | 1418 | 1494 |
| LMArena French | 1459 | — |
| LMArena German | 1447 | — |
| LMArena Japanese | 1394 | — |
| LMArena Korean | 1401 | — |
| LMArena Spanish | 1436 | — |
Instruction Following Muse Spark 1.2 leads
GLM-4.6: 74.5 (#93), Muse Spark 1.2: 77.1 (#30)
| Benchmark | GLM-4.6 | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1410 | 1466 |
Long Context Muse Spark 1.2 leads
GLM-4.6: 43.4 (#91), Muse Spark 1.2: 45.4 (#35)
| Benchmark | GLM-4.6 | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1423 | 1483 |
Writing & Preference Muse Spark 1.2 leads
GLM-4.6: 61.3 (#86), Muse Spark 1.2: 72.6 (#14)
| Benchmark | GLM-4.6 | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1440 | 1486 |
| LMArena Creative Writing | 1411 | 1444 |
| EQ-Bench Creative Writing | 1411 | 1840 |
| LMArena Multi-Turn | 1427 | 1504 |
Frequently asked questions
Is GLM-4.6 better than Muse Spark 1.2?
Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 40.9 on the Noometry Index. GLM-4.6 costs 2.0× 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-4.6 or Muse Spark 1.2?
GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.
Is GLM-4.6 or Muse Spark 1.2 better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 48.6 versus 39.9 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.2 does, with 1.05M tokens against 205K.
How many benchmarks do GLM-4.6 and Muse Spark 1.2 share?
15 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Muse Spark 1.2 has 28.