Model comparison
GLM-4.7 vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.6 to 42.0 on the Noometry Index.
Last verified . 24 shared benchmarks.
MetaSummary
- They share 24 benchmarks with published results for both. GLM-4.7 scores higher in 0 categories and Muse Spark in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 47.0.
- The biggest single-benchmark swing is ProofBench: 6% for GLM-4.7 and 17% for Muse Spark.
- GLM-4.7 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.7 | Muse Spark | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 42.0 | 50.6 |
| Released | 2025-12-22 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 36 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
GLM-4.7: 44.0 (#79), Muse Spark: 46.2 (#69)
| Benchmark | GLM-4.7 | Muse Spark |
|---|---|---|
| SciCode | 45.1% | 51.5% |
| LMArena Coding | 1454 | 1481 |
| LMArena WebDev | 1435 | — |
| ALE-Bench | 399.48 | — |
Agentic & Tool Use Not comparable
GLM-4.7: 26.5 (#103), Muse Spark: —
| Benchmark | GLM-4.7 | Muse Spark |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| Vending-Bench 2 | 2,377 | — |
Reasoning Muse Spark leads
GLM-4.7: 24.3 (#164), Muse Spark: 35.9 (#67)
| Benchmark | GLM-4.7 | Muse Spark |
|---|---|---|
| CritPt | 1.7% | 11.3% |
| LMArena Hard Prompts | 1443 | 1474 |
| Epoch Capabilities Index | 143.51 | 152.04 |
| SimpleBench | 47.7% | — |
| Chess Puzzles | 6% | — |
Math Muse Spark leads
GLM-4.7: 38.6 (#135), Muse Spark: 47.8 (#66)
| Benchmark | GLM-4.7 | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 88.9% |
| ProofBench | 6% | 17% |
| LMArena Math | 1423 | 1455 |
| FrontierMath (Feb 2025 set) | 2.4% | 39% |
| FrontierMath Tier 4 (v1) | 0% | 14.6% |
Knowledge Muse Spark leads
GLM-4.7: 47.0 (#80), Muse Spark: 65.7 (#13)
| Benchmark | GLM-4.7 | Muse Spark |
|---|---|---|
| GPQA Diamond | 83.3% | 89.8% |
| LMArena Expert | 1424 | 1457 |
| Humanity's Last Exam | — | 40.6% |
| SimpleQA Verified | 32.2% | — |
| Vectara Hallucination Rate | 11.7% | — |
Multimodal Not comparable
GLM-4.7: —, Muse Spark: 43.4 (#24)
| Benchmark | GLM-4.7 | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Muse Spark leads
GLM-4.7: 52.8 (#79), Muse Spark: 56.1 (#24)
| Benchmark | GLM-4.7 | Muse Spark |
|---|---|---|
| LMArena Non-English | 1417 | 1464 |
| LMArena Chinese | 1495 | 1509 |
| LMArena French | 1432 | 1497 |
| LMArena German | 1424 | 1497 |
| LMArena Korean | 1399 | 1459 |
| LMArena Russian | 1423 | 1466 |
| LMArena Spanish | 1434 | 1472 |
| LMArena Japanese | 1439 | — |
Instruction Following Muse Spark leads
GLM-4.7: 74.4 (#95), Muse Spark: 75.9 (#51)
| Benchmark | GLM-4.7 | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1411 | 1442 |
Long Context Muse Spark leads
GLM-4.7: 42.8 (#116), Muse Spark: 44.4 (#69)
| Benchmark | GLM-4.7 | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1432 | 1451 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
Writing & Preference Muse Spark leads
GLM-4.7: 60.9 (#93), Muse Spark: 66.0 (#39)
| Benchmark | GLM-4.7 | Muse Spark |
|---|---|---|
| LMArena Text | 1435 | 1474 |
| LMArena Creative Writing | 1401 | 1459 |
| LMArena Multi-Turn | 1446 | 1477 |
| EQ-Bench Creative Writing | 1413 | — |
Frequently asked questions
Is GLM-4.7 better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.6 to 42.0 on the Noometry Index.
Is GLM-4.7 or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 44.0 in the Noometry coding category.
How many benchmarks do GLM-4.7 and Muse Spark share?
24 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Muse Spark has 27.