Model comparison
Claude Sonnet 5 vs Hy3
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 44.2 on the Noometry Index. Hy3 costs 28× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
TencentSummary
- They share 19 benchmarks with published results for both. Claude Sonnet 5 scores higher in 8 categories and Hy3 in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.2 to 40.1.
- The biggest single-benchmark swing is NYT Connections (extended): 75.1% for Claude Sonnet 5 and 41.2% for Hy3.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- Claude Sonnet 5 accepts more context: 1M tokens versus 262K.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 5 | Hy3 | |
|---|---|---|
| Provider | Anthropic | Tencent |
| Noometry Index | 54.6 | 44.2 |
| Released | 2026-06-29 | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | 1M | 262K |
| Max output | 128K | 128K |
| Input $ / M tokens | $2 | $0.0825 |
| Output $ / M tokens | $10 | $0.33 |
| Results tracked | 51 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude Sonnet 5: 55.5 (#26), Hy3: 46.8 (#63)
| Benchmark | Claude Sonnet 5 | Hy3 |
|---|---|---|
| LMArena WebDev | 1541 | 1508 |
| LMArena Coding | 1483 | 1464 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| CursorBench | 34.1% | — |
| SciCode | 54.3% | — |
| GSO | 37.3% | — |
| WeirdML | 68.8% | — |
| ALE-Bench | 1,463 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 5: 42.8 (#18), Hy3: —
| Benchmark | Claude Sonnet 5 | Hy3 |
|---|---|---|
| APEX-Agents | 54.5% | — |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |
Reasoning Claude Sonnet 5 leads
Claude Sonnet 5: 49.1 (#39), Hy3: 26.1 (#136)
| Benchmark | Claude Sonnet 5 | Hy3 |
|---|---|---|
| NYT Connections (extended) | 75.1% | 41.2% |
| LMArena Hard Prompts | 1461 | 1447 |
| SimpleBench | 60.6% | — |
| CritPt | 16.9% | — |
| Chess Puzzles | 35% | — |
| Mystery Game Puzzles | 35% | — |
| DTBench | 92.5% | — |
| LMCA | 50% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| Epoch Capabilities Index | 156.21 | — |
| ForecastBench | 61.1 | — |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.2 (#27), Hy3: 40.1 (#93)
| Benchmark | Claude Sonnet 5 | Hy3 |
|---|---|---|
| LMArena Math | 1467 | 1475 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| OTIS Mock AIME 2024-2025 | 94.7% | — |
| ProofBench | 77% | — |
Knowledge Claude Sonnet 5 leads
Claude Sonnet 5: 55.6 (#47), Hy3: 40.8 (#114)
| Benchmark | Claude Sonnet 5 | Hy3 |
|---|---|---|
| LMArena Expert | 1490 | 1460 |
| GPQA Diamond | 90.5% | — |
| SimpleQA Verified | 33.7% | — |
Multimodal Not comparable
Claude Sonnet 5: 42.4 (#31), Hy3: —
| Benchmark | Claude Sonnet 5 | Hy3 |
|---|---|---|
| LMArena Vision | 1274 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |
Multilingual Too close to call
Claude Sonnet 5: 53.8 (#55), Hy3: 53.5 (#65)
| Benchmark | Claude Sonnet 5 | Hy3 |
|---|---|---|
| LMArena Non-English | 1431 | 1426 |
| LMArena Chinese | 1477 | 1493 |
| LMArena French | 1460 | 1461 |
| LMArena German | 1440 | 1439 |
| LMArena Japanese | 1422 | 1392 |
| LMArena Korean | 1411 | 1395 |
| LMArena Russian | 1451 | 1432 |
| LMArena Spanish | 1437 | 1456 |
Instruction Following Claude Sonnet 5 leads
Claude Sonnet 5: 76.3 (#41), Hy3: 75.1 (#70)
| Benchmark | Claude Sonnet 5 | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1452 | 1426 |
Long Context Too close to call
Claude Sonnet 5: 44.8 (#55), Hy3: 44.1 (#75)
| Benchmark | Claude Sonnet 5 | Hy3 |
|---|---|---|
| LMArena Longer Query | 1463 | 1442 |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.2 (#25), Hy3: 62.2 (#81)
| Benchmark | Claude Sonnet 5 | Hy3 |
|---|---|---|
| LMArena Text | 1442 | 1439 |
| LMArena Creative Writing | 1416 | 1402 |
| LMArena Multi-Turn | 1454 | 1436 |
| EQ-Bench Creative Writing | 1794 | — |
| EQ-Bench 4 | 1236 | — |
Frequently asked questions
Is Claude Sonnet 5 better than Hy3?
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 44.2 on the Noometry Index. Hy3 costs 28× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 5 or Hy3?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Claude Sonnet 5 lists at $2 and $10.
Is Claude Sonnet 5 or Hy3 better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 46.8 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 5 does, with 1M tokens against 262K.
How many benchmarks do Claude Sonnet 5 and Hy3 share?
19 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Hy3 has 19.