Model comparison
Hy3 vs Sonar
Hy3 is the stronger model overall, scoring 43.6 to 37.8 on the Noometry Index.
Last verified . 0 shared benchmarks.
Tencent
PerplexitySummary
- The widest gap is in coding, where Hy3 leads 46.6 to 35.1.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $1 / $1 for Sonar.
- Hy3 accepts more context: 262K tokens versus 128K.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Hy3 | Sonar | |
|---|---|---|
| Provider | Tencent | Perplexity |
| Noometry Index | 43.6 | 37.8 |
| Released | 2026-07-06 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 262K | 128K |
| Max output | 128K | 4K |
| Input $ / M tokens | $0.13 | $1 |
| Output $ / M tokens | $0.53 | $1 |
| Results tracked | 17 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.6 (#60), Sonar: 35.1 (#217)
| Benchmark | Hy3 | Sonar |
|---|---|---|
| LMArena WebDev | 1509 | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1465 | — |
Reasoning Hy3 leads
Hy3: 25.0 (#134), Sonar: 20.3 (#221)
| Benchmark | Hy3 | Sonar |
|---|---|---|
| NYT Connections (extended) | 41.2% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1449 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |
Math Hy3 leads
Hy3: 37.4 (#98), Sonar: 31.3 (#197)
| Benchmark | Hy3 | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1475 | — |
Knowledge Not comparable
Hy3: 40.2 (#108), Sonar: —
| Benchmark | Hy3 | Sonar |
|---|---|---|
| LMArena Expert | 1461 | — |
Multilingual Not comparable
Hy3: 53.7 (#60), Sonar: —
| Benchmark | Hy3 | Sonar |
|---|---|---|
| LMArena Non-English | 1427 | — |
| LMArena Chinese | 1496 | — |
| LMArena French | 1461 | — |
| LMArena Korean | 1390 | — |
| LMArena Russian | 1435 | — |
| LMArena Spanish | 1448 | — |
Instruction Following Hy3 leads
Hy3: 75.3 (#68), Sonar: 71.5 (#146)
| Benchmark | Hy3 | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1425 | — |
Long Context Not comparable
Hy3: 44.1 (#70), Sonar: —
| Benchmark | Hy3 | Sonar |
|---|---|---|
| LMArena Longer Query | 1443 | — |
Writing & Preference Hy3 leads
Hy3: 62.5 (#75), Sonar: 52.6 (#166)
| Benchmark | Hy3 | Sonar |
|---|---|---|
| LMArena Text | 1442 | — |
| LMArena Creative Writing | 1399 | — |
| LMArena Multi-Turn | 1436 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Hy3 better than Sonar?
Hy3 is the stronger model overall, scoring 43.6 to 37.8 on the Noometry Index.
Which is cheaper, Hy3 or Sonar?
Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; Sonar lists at $1 and $1.
Is Hy3 or Sonar better for coding?
Hy3 scores higher on coding benchmarks: 46.6 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
Hy3 does, with 262K tokens against 128K.
How many benchmarks do Hy3 and Sonar share?
0 benchmarks have published results for both models. Hy3 has 17 scored results on Noometry and Sonar has 7.