Model comparison
Hy3 vs Muse Spark 1.1
Muse Spark 1.1 is the stronger model overall, scoring 49.9 to 43.6 on the Noometry Index. Hy3 costs 8.7× less per token, which makes it the better buy when Muse Spark 1.1's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Tencent
MetaSummary
- They share 17 benchmarks with published results for both. Hy3 scores higher in 0 categories and Muse Spark 1.1 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.1 leads 45.9 to 25.0.
- The biggest single-benchmark swing is NYT Connections (extended): 41.2% for Hy3 and 84.9% for Muse Spark 1.1.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.1.
- Muse Spark 1.1 accepts more context: 1.05M tokens versus 262K.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Hy3 | Muse Spark 1.1 | |
|---|---|---|
| Provider | Tencent | Meta |
| Noometry Index | 43.6 | 49.9 |
| Released | 2026-07-06 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 262K | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.13 | $1.25 |
| Output $ / M tokens | $0.53 | $4.25 |
| Results tracked | 17 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.1 leads
Hy3: 46.6 (#60), Muse Spark 1.1: 50.8 (#38)
| Benchmark | Hy3 | Muse Spark 1.1 |
|---|---|---|
| LMArena WebDev | 1509 | 1542 |
| LMArena Coding | 1465 | 1497 |
| DeepSWE | — | 53.3% |
| SciCode | — | 58.8% |
Agentic & Tool Use Not comparable
Hy3: —, Muse Spark 1.1: 33.9 (#45)
| Benchmark | Hy3 | Muse Spark 1.1 |
|---|---|---|
| τ²-bench Banking | — | 40.5% |
| GBAEval | — | 7.9% |
| GDP.pdf | — | 15% |
| Vending-Bench 2 | — | 6,520 |
Reasoning Muse Spark 1.1 leads
Hy3: 25.0 (#134), Muse Spark 1.1: 45.9 (#41)
| Benchmark | Hy3 | Muse Spark 1.1 |
|---|---|---|
| NYT Connections (extended) | 41.2% | 84.9% |
| LMArena Hard Prompts | 1449 | 1486 |
| CritPt | — | 15.1% |
| DTBench | — | 94.4% |
| LMCA | — | 49.9% |
| Surface Evolver Bench | — | 52.5% |
| Epoch Capabilities Index | — | 154.32 |
Math Muse Spark 1.1 leads
Hy3: 37.4 (#98), Muse Spark 1.1: 44.0 (#67)
| Benchmark | Hy3 | Muse Spark 1.1 |
|---|---|---|
| LMArena Math | 1475 | 1477 |
| ProofBench | — | 39% |
Knowledge Muse Spark 1.1 leads
Hy3: 40.2 (#108), Muse Spark 1.1: 52.8 (#55)
| Benchmark | Hy3 | Muse Spark 1.1 |
|---|---|---|
| LMArena Expert | 1461 | 1480 |
| SimpleQA Verified | — | 57.8% |
Multimodal Not comparable
Hy3: —, Muse Spark 1.1: 41.9 (#28)
| Benchmark | Hy3 | Muse Spark 1.1 |
|---|---|---|
| LMArena Vision | — | 1292 |
| LMArena Document | — | 1465 |
Multilingual Muse Spark 1.1 leads
Hy3: 53.7 (#60), Muse Spark 1.1: 56.8 (#16)
| Benchmark | Hy3 | Muse Spark 1.1 |
|---|---|---|
| LMArena Non-English | 1427 | 1471 |
| LMArena Chinese | 1496 | 1518 |
| LMArena French | 1461 | 1494 |
| LMArena Korean | 1390 | 1459 |
| LMArena Russian | 1435 | 1482 |
| LMArena Spanish | 1448 | 1471 |
| LMArena German | — | 1466 |
| LMArena Japanese | — | 1445 |
Instruction Following Muse Spark 1.1 leads
Hy3: 75.3 (#68), Muse Spark 1.1: 76.8 (#36)
| Benchmark | Hy3 | Muse Spark 1.1 |
|---|---|---|
| LMArena Instruction Following | 1425 | 1457 |
Long Context Too close to call
Hy3: 44.1 (#70), Muse Spark 1.1: 44.8 (#55)
| Benchmark | Hy3 | Muse Spark 1.1 |
|---|---|---|
| LMArena Longer Query | 1443 | 1463 |
Writing & Preference Muse Spark 1.1 leads
Hy3: 62.5 (#75), Muse Spark 1.1: 73.6 (#11)
| Benchmark | Hy3 | Muse Spark 1.1 |
|---|---|---|
| LMArena Text | 1442 | 1479 |
| LMArena Creative Writing | 1399 | 1440 |
| LMArena Multi-Turn | 1436 | 1484 |
| EQ-Bench Creative Writing | — | 1927 |
| EQ-Bench 4 | — | 1260 |
Frequently asked questions
Is Hy3 better than Muse Spark 1.1?
Muse Spark 1.1 is the stronger model overall, scoring 49.9 to 43.6 on the Noometry Index. Hy3 costs 8.7× less per token, which makes it the better buy when Muse Spark 1.1's lead doesn't matter for your workload.
Which is cheaper, Hy3 or Muse Spark 1.1?
Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; Muse Spark 1.1 lists at $1.25 and $4.25.
Is Hy3 or Muse Spark 1.1 better for coding?
Muse Spark 1.1 scores higher on coding benchmarks: 50.8 versus 46.6 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.1 does, with 1.05M tokens against 262K.
How many benchmarks do Hy3 and Muse Spark 1.1 share?
17 benchmarks have published results for both models. Hy3 has 17 scored results on Noometry and Muse Spark 1.1 has 36.