Model comparison
Hy4 preview vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 45.3 on the Noometry Index. Hy4 preview costs 1.8× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
Tencent
MetaSummary
- They share 3 benchmarks with published results for both. Hy4 preview scores higher in 0 categories and Muse Spark 1.3 in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.3 leads 54.0 to 31.9.
- The biggest single-benchmark swing is ProofBench: 75% for Hy4 preview and 58% for Muse Spark 1.3.
- Hy4 preview is cheaper at $0.75 / $2.25 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.3.
- Hy4 preview has downloadable open weights; the other is API-only.
Side by side
| Hy4 preview | Muse Spark 1.3 | |
|---|---|---|
| Provider | Tencent | Meta |
| Noometry Index | 45.3 | 54.8 |
| Released | 2026-08-28 | 2026-09-02 |
| Weights | Open | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 64K | 131K |
| Input $ / M tokens | $0.75 | $1.25 |
| Output $ / M tokens | $2.25 | $4.25 |
| Results tracked | 3 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
Hy4 preview: 51.6 (#38), Muse Spark 1.3: 56.6 (#21)
| Benchmark | Hy4 preview | Muse Spark 1.3 |
|---|---|---|
| LMArena WebDev | 1632 | 1657 |
| CursorBench | — | 41.6% |
| SciCode | — | 59.7% |
| LMArena Coding | — | 1514 |
Agentic & Tool Use Not comparable
Hy4 preview: —, Muse Spark 1.3: 38.6 (#30)
| Benchmark | Hy4 preview | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | — | 57.8% |
| GDP.pdf | — | 27.6% |
Reasoning Muse Spark 1.3 leads
Hy4 preview: 31.9 (#79), Muse Spark 1.3: 54.0 (#27)
| Benchmark | Hy4 preview | Muse Spark 1.3 |
|---|---|---|
| NYT Connections (extended) | 68.2% | 85.1% |
| CritPt | — | 26% |
| Chess Puzzles | — | 38% |
| LMArena Hard Prompts | — | 1503 |
| Mystery Game Puzzles | — | 25% |
| DTBench | — | 96.5% |
| LMCA | — | 53.9% |
| Bench to the Future 3 | — | 0.14 |
| Epoch Capabilities Index | — | 156.75 |
Math Muse Spark 1.3 leads
Hy4 preview: 55.7 (#42), Muse Spark 1.3: 73.1 (#21)
| Benchmark | Hy4 preview | Muse Spark 1.3 |
|---|---|---|
| ProofBench | 75% | 58% |
| FrontierMath (Tiers 1-3) | — | 74.4% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 99.2% |
| LMArena Math | — | 1494 |
Knowledge Not comparable
Hy4 preview: —, Muse Spark 1.3: 42.6 (#95)
| Benchmark | Hy4 preview | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | — | 1516 |
Multimodal Not comparable
Hy4 preview: —, Muse Spark 1.3: 43.7 (#22)
| Benchmark | Hy4 preview | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | — | 1309 |
| LMArena Document | — | 1471 |
Multilingual Not comparable
Hy4 preview: —, Muse Spark 1.3: 57.4 (#8)
| Benchmark | Hy4 preview | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | — | 1481 |
| LMArena Chinese | — | 1529 |
| LMArena French | — | 1524 |
| LMArena German | — | 1515 |
| LMArena Japanese | — | 1474 |
| LMArena Korean | — | 1501 |
| LMArena Russian | — | 1490 |
| LMArena Spanish | — | 1490 |
Instruction Following Not comparable
Hy4 preview: —, Muse Spark 1.3: 77.5 (#22)
| Benchmark | Hy4 preview | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | — | 1477 |
Long Context Not comparable
Hy4 preview: —, Muse Spark 1.3: 45.6 (#32)
| Benchmark | Hy4 preview | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | — | 1488 |
Writing & Preference Not comparable
Hy4 preview: —, Muse Spark 1.3: 73.6 (#9)
| Benchmark | Hy4 preview | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | — | 1490 |
| LMArena Creative Writing | — | 1455 |
| EQ-Bench Creative Writing | — | 1906 |
| LMArena Multi-Turn | — | 1482 |
Frequently asked questions
Is Hy4 preview better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 45.3 on the Noometry Index. Hy4 preview costs 1.8× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Which is cheaper, Hy4 preview or Muse Spark 1.3?
Hy4 preview is cheaper. It lists at $0.75 per million input tokens and $2.25 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.
Is Hy4 preview or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 51.6 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do Hy4 preview and Muse Spark 1.3 share?
3 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Muse Spark 1.3 has 37.