Model comparison
Hy3 vs Qwen Plus
Hy3 is the stronger model overall, scoring 44.2 to 37.1 on the Noometry Index.
Last verified . 13 shared benchmarks.
Tencent
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Hy3 scores higher in 7 categories and Qwen Plus in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy3 leads 40.1 to 23.3.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $0.40 / $1.20 for Qwen Plus.
- Qwen Plus accepts more context: 1M tokens versus 262K.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Hy3 | Qwen Plus | |
|---|---|---|
| Provider | Tencent | Alibaba (Qwen) |
| Noometry Index | 44.2 | 37.1 |
| Released | 2026-07-06 | 2024-01-25 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 128K | 33K |
| Input $ / M tokens | $0.0825 | $0.40 |
| Output $ / M tokens | $0.33 | $1.20 |
| Results tracked | 19 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Qwen Plus: 38.9 (#167)
| Benchmark | Hy3 | Qwen Plus |
|---|---|---|
| LMArena Coding | 1464 | 1328 |
| LMArena WebDev | 1508 | — |
Reasoning Qwen Plus leads
Hy3: 26.1 (#136), Qwen Plus: 28.4 (#107)
| Benchmark | Hy3 | Qwen Plus |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1317 |
| Kagi LLM Benchmark | — | 63.3% |
| NYT Connections (extended) | 41.2% | — |
| DTBench | — | 81.1% |
| LMCA | — | 24% |
Math Hy3 leads
Hy3: 40.1 (#93), Qwen Plus: 23.3 (#271)
| Benchmark | Hy3 | Qwen Plus |
|---|---|---|
| LMArena Math | 1475 | 1326 |
| OTIS Mock AIME 2024-2025 | — | 17.8% |
| MATH Level 5 | — | 65.3% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Qwen Plus: 27.4 (#251)
| Benchmark | Hy3 | Qwen Plus |
|---|---|---|
| LMArena Expert | 1460 | 1328 |
| GPQA Diamond | — | 48.1% |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Qwen Plus: 45.1 (#175)
| Benchmark | Hy3 | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1426 | 1310 |
| LMArena Chinese | 1493 | 1347 |
| LMArena Japanese | 1392 | 1251 |
| LMArena Russian | 1432 | 1323 |
| LMArena French | 1461 | — |
| LMArena German | 1439 | — |
| LMArena Korean | 1395 | — |
| LMArena Spanish | 1456 | — |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Qwen Plus: 68.8 (#181)
| Benchmark | Hy3 | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1426 | 1303 |
Long Context Hy3 leads
Hy3: 44.1 (#75), Qwen Plus: 40.3 (#158)
| Benchmark | Hy3 | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1442 | 1324 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Qwen Plus: 52.2 (#176)
| Benchmark | Hy3 | Qwen Plus |
|---|---|---|
| LMArena Text | 1439 | 1326 |
| LMArena Creative Writing | 1402 | 1293 |
| LMArena Multi-Turn | 1436 | 1336 |
Frequently asked questions
Is Hy3 better than Qwen Plus?
Hy3 is the stronger model overall, scoring 44.2 to 37.1 on the Noometry Index.
Which is cheaper, Hy3 or Qwen Plus?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Qwen Plus lists at $0.40 and $1.20.
Is Hy3 or Qwen Plus better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 38.9 in the Noometry coding category.
Which has the bigger context window?
Qwen Plus does, with 1M tokens against 262K.
How many benchmarks do Hy3 and Qwen Plus share?
13 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Qwen Plus has 20.