Model comparison
Hy3 vs Qwen3-Coder 480B-A35B Instruct
Hy3 is the stronger model overall, scoring 44.2 to 38.1 on the Noometry Index.
Last verified . 18 shared benchmarks.
Tencent
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Hy3 scores higher in 8 categories and Qwen3-Coder 480B-A35B Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Hy3 leads 46.8 to 35.5.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
Side by side
| Hy3 | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | Tencent | Alibaba (Qwen) |
| Noometry Index | 44.2 | 38.1 |
| Released | 2026-07-06 | 2025-04 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 128K | 66K |
| Input $ / M tokens | $0.13 | $1.50 |
| Output $ / M tokens | $0.53 | $7.50 |
| Results tracked | 19 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)
| Benchmark | Hy3 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena WebDev | 1508 | 1275 |
| LMArena Coding | 1464 | 1412 |
| SWE-bench Verified (bash only) | — | 55.4% |
| GSO | — | 4.9% |
| WeirdML | — | 41.2% |
| ALE-Bench | — | 461.45 |
| AlgoTune | — | 1.44 |
Agentic & Tool Use Not comparable
Hy3: —, Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)
| Benchmark | Hy3 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
Reasoning Too close to call
Hy3: 26.1 (#136), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)
| Benchmark | Hy3 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1372 |
| Kagi LLM Benchmark | — | 49.5% |
| NYT Connections (extended) | 41.2% | — |
Math Hy3 leads
Hy3: 40.1 (#93), Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)
| Benchmark | Hy3 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1475 | 1365 |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)
| Benchmark | Hy3 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1460 | 1338 |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)
| Benchmark | Hy3 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1426 | 1346 |
| LMArena Chinese | 1493 | 1357 |
| LMArena French | 1461 | 1398 |
| LMArena German | 1439 | 1325 |
| LMArena Japanese | 1392 | 1310 |
| LMArena Korean | 1395 | 1305 |
| LMArena Russian | 1432 | 1366 |
| LMArena Spanish | 1456 | 1360 |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)
| Benchmark | Hy3 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1426 | 1355 |
Long Context Hy3 leads
Hy3: 44.1 (#75), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)
| Benchmark | Hy3 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1442 | 1378 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)
| Benchmark | Hy3 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1439 | 1357 |
| LMArena Creative Writing | 1402 | 1333 |
| LMArena Multi-Turn | 1436 | 1365 |
Frequently asked questions
Is Hy3 better than Qwen3-Coder 480B-A35B Instruct?
Hy3 is the stronger model overall, scoring 44.2 to 38.1 on the Noometry Index.
Which is cheaper, Hy3 or Qwen3-Coder 480B-A35B Instruct?
Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.
Is Hy3 or Qwen3-Coder 480B-A35B Instruct better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 35.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Hy3 and Qwen3-Coder 480B-A35B Instruct share?
18 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.