Model comparison
GLM-5 vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.6 to 46.1 on the Noometry Index.
Last verified . 21 shared benchmarks.
MetaSummary
- They share 21 benchmarks with published results for both. GLM-5 scores higher in 3 categories and Muse Spark in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 52.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 80% for GLM-5 and 88.9% for Muse Spark.
- GLM-5 has downloadable open weights; the other is API-only.
Side by side
| GLM-5 | Muse Spark | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 46.1 | 50.6 |
| Released | 2026-02-11 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 45 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), Muse Spark: 46.2 (#69)
| Benchmark | GLM-5 | Muse Spark |
|---|---|---|
| LMArena Coding | 1461 | 1481 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| SciCode | — | 51.5% |
| WeirdML | 48.2% | — |
| ALE-Bench | 765.62 | — |
Agentic & Tool Use Not comparable
GLM-5: 31.1 (#71), Muse Spark: —
| Benchmark | GLM-5 | Muse Spark |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| Vending-Bench 2 | 4,432 | — |
Reasoning Muse Spark leads
GLM-5: 27.6 (#116), Muse Spark: 35.9 (#67)
| Benchmark | GLM-5 | Muse Spark |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1474 |
| Epoch Capabilities Index | 145.83 | 152.04 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 53.2% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 74.8% | — |
| ARC-AGI-1 | 44.7% | — |
| CritPt | — | 11.3% |
| Chess Puzzles | 10% | — |
| ForecastBench | 61 | — |
Math Muse Spark leads
GLM-5: 46.4 (#71), Muse Spark: 47.8 (#66)
| Benchmark | GLM-5 | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 88.9% |
| LMArena Math | 1440 | 1455 |
| FrontierMath (Feb 2025 set) | 16.4% | 39% |
| FrontierMath Tier 4 (v1) | 2.1% | 14.6% |
| MathArena Final-Answer Competitions | 65.7% | — |
| ProofBench | — | 17% |
Knowledge Muse Spark leads
GLM-5: 52.3 (#64), Muse Spark: 65.7 (#13)
| Benchmark | GLM-5 | Muse Spark |
|---|---|---|
| GPQA Diamond | 87.8% | 89.8% |
| LMArena Expert | 1454 | 1457 |
| Humanity's Last Exam | — | 40.6% |
| Vectara Hallucination Rate | 10.1% | — |
Multimodal Not comparable
GLM-5: —, Muse Spark: 43.4 (#24)
| Benchmark | GLM-5 | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Muse Spark leads
GLM-5: 53.7 (#58), Muse Spark: 56.1 (#24)
| Benchmark | GLM-5 | Muse Spark |
|---|---|---|
| LMArena Non-English | 1430 | 1464 |
| LMArena Chinese | 1511 | 1509 |
| LMArena French | 1455 | 1497 |
| LMArena German | 1445 | 1497 |
| LMArena Korean | 1423 | 1459 |
| LMArena Russian | 1436 | 1466 |
| LMArena Spanish | 1454 | 1472 |
| LMArena Japanese | 1416 | — |
Instruction Following Too close to call
GLM-5: 75.2 (#67), Muse Spark: 75.9 (#51)
| Benchmark | GLM-5 | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1428 | 1442 |
Long Context Too close to call
GLM-5: 44.7 (#60), Muse Spark: 44.4 (#69)
| Benchmark | GLM-5 | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1446 | 1451 |
| CL-bench | 18.7% | — |
Writing & Preference Too close to call
GLM-5: 66.0 (#38), Muse Spark: 66.0 (#39)
| Benchmark | GLM-5 | Muse Spark |
|---|---|---|
| LMArena Text | 1446 | 1474 |
| LMArena Creative Writing | 1439 | 1459 |
| LMArena Multi-Turn | 1456 | 1477 |
| EQ-Bench Creative Writing | 1601 | — |
Frequently asked questions
Is GLM-5 better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.6 to 46.1 on the Noometry Index.
Is GLM-5 or Muse Spark better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 46.2 in the Noometry coding category.
How many benchmarks do GLM-5 and Muse Spark share?
21 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Muse Spark has 27.