Model comparison
Hy4 preview vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.6 to 45.3 on the Noometry Index.
Last verified . 1 shared benchmarks.
Tencent
MetaSummary
- They share 1 benchmark with published results for both. Hy4 preview scores higher in 2 categories and Muse Spark in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy4 preview leads 55.7 to 47.8.
- The biggest single-benchmark swing is ProofBench: 75% for Hy4 preview and 17% for Muse Spark.
- Hy4 preview has downloadable open weights; the other is API-only.
Side by side
| Hy4 preview | Muse Spark | |
|---|---|---|
| Provider | Tencent | Meta |
| Noometry Index | 45.3 | 50.6 |
| Released | 2026-08-28 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 1.05M | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.75 | — |
| Output $ / M tokens | $2.25 | — |
| Results tracked | 3 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Hy4 preview: 51.6 (#38), Muse Spark: 46.2 (#69)
| Benchmark | Hy4 preview | Muse Spark |
|---|---|---|
| LMArena WebDev | 1632 | — |
| SciCode | — | 51.5% |
| LMArena Coding | — | 1481 |
Reasoning Muse Spark leads
Hy4 preview: 31.9 (#79), Muse Spark: 35.9 (#67)
| Benchmark | Hy4 preview | Muse Spark |
|---|---|---|
| NYT Connections (extended) | 68.2% | — |
| CritPt | — | 11.3% |
| LMArena Hard Prompts | — | 1474 |
| Epoch Capabilities Index | — | 152.04 |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), Muse Spark: 47.8 (#66)
| Benchmark | Hy4 preview | Muse Spark |
|---|---|---|
| ProofBench | 75% | 17% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| LMArena Math | — | 1455 |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Not comparable
Hy4 preview: —, Muse Spark: 65.7 (#13)
| Benchmark | Hy4 preview | Muse Spark |
|---|---|---|
| GPQA Diamond | — | 89.8% |
| Humanity's Last Exam | — | 40.6% |
| LMArena Expert | — | 1457 |
Multimodal Not comparable
Hy4 preview: —, Muse Spark: 43.4 (#24)
| Benchmark | Hy4 preview | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Not comparable
Hy4 preview: —, Muse Spark: 56.1 (#24)
| Benchmark | Hy4 preview | Muse Spark |
|---|---|---|
| LMArena Non-English | — | 1464 |
| LMArena Chinese | — | 1509 |
| LMArena French | — | 1497 |
| LMArena German | — | 1497 |
| LMArena Korean | — | 1459 |
| LMArena Russian | — | 1466 |
| LMArena Spanish | — | 1472 |
Instruction Following Not comparable
Hy4 preview: —, Muse Spark: 75.9 (#51)
| Benchmark | Hy4 preview | Muse Spark |
|---|---|---|
| LMArena Instruction Following | — | 1442 |
Long Context Not comparable
Hy4 preview: —, Muse Spark: 44.4 (#69)
| Benchmark | Hy4 preview | Muse Spark |
|---|---|---|
| LMArena Longer Query | — | 1451 |
Writing & Preference Not comparable
Hy4 preview: —, Muse Spark: 66.0 (#39)
| Benchmark | Hy4 preview | Muse Spark |
|---|---|---|
| LMArena Text | — | 1474 |
| LMArena Creative Writing | — | 1459 |
| LMArena Multi-Turn | — | 1477 |
Frequently asked questions
Is Hy4 preview better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.6 to 45.3 on the Noometry Index.
Is Hy4 preview or Muse Spark better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 46.2 in the Noometry coding category.
How many benchmarks do Hy4 preview and Muse Spark share?
1 benchmark has published results for both models. Hy4 preview has 3 scored results on Noometry and Muse Spark has 27.