Model comparison
Claude 3 Sonnet vs Hy3
Hy3 is the stronger model overall, scoring 44.2 to 29.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
TencentSummary
- They share 17 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Hy3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy3 leads 40.1 to 10.7.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Sonnet | Hy3 | |
|---|---|---|
| Provider | Anthropic | Tencent |
| Noometry Index | 29.0 | 44.2 |
| Released | 2024-02-29 | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.0825 |
| Output $ / M tokens | — | $0.33 |
| Results tracked | 30 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Claude 3 Sonnet: 29.6 (#302), Hy3: 46.8 (#63)
| Benchmark | Claude 3 Sonnet | Hy3 |
|---|---|---|
| LMArena Coding | 1223 | 1464 |
| LMArena WebDev | — | 1508 |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |
Reasoning Hy3 leads
Claude 3 Sonnet: 20.5 (#237), Hy3: 26.1 (#136)
| Benchmark | Claude 3 Sonnet | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1447 |
| NYT Connections (extended) | — | 41.2% |
| DTBench | 53.6% | — |
| Epoch Capabilities Index | 120.7 | — |
| WinoGrande | 75.1% | — |
Math Hy3 leads
Claude 3 Sonnet: 10.7 (#310), Hy3: 40.1 (#93)
| Benchmark | Claude 3 Sonnet | Hy3 |
|---|---|---|
| LMArena Math | 1213 | 1475 |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| MATH Level 5 | 18.2% | — |
Knowledge Hy3 leads
Claude 3 Sonnet: 21.1 (#276), Hy3: 40.8 (#114)
| Benchmark | Claude 3 Sonnet | Hy3 |
|---|---|---|
| LMArena Expert | 1173 | 1460 |
| GPQA Diamond | 40.6% | — |
| MMLU | 75.9% | — |
Multimodal Not comparable
Claude 3 Sonnet: 25.2 (#125), Hy3: —
| Benchmark | Claude 3 Sonnet | Hy3 |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual Hy3 leads
Claude 3 Sonnet: 37.8 (#234), Hy3: 53.5 (#65)
| Benchmark | Claude 3 Sonnet | Hy3 |
|---|---|---|
| LMArena Non-English | 1205 | 1426 |
| LMArena Chinese | 1189 | 1493 |
| LMArena French | 1229 | 1461 |
| LMArena German | 1204 | 1439 |
| LMArena Japanese | 1131 | 1392 |
| LMArena Korean | 1128 | 1395 |
| LMArena Russian | 1227 | 1432 |
| LMArena Spanish | 1204 | 1456 |
Instruction Following Hy3 leads
Claude 3 Sonnet: 62.8 (#235), Hy3: 75.1 (#70)
| Benchmark | Claude 3 Sonnet | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1199 | 1426 |
Long Context Hy3 leads
Claude 3 Sonnet: 36.7 (#228), Hy3: 44.1 (#75)
| Benchmark | Claude 3 Sonnet | Hy3 |
|---|---|---|
| LMArena Longer Query | 1211 | 1442 |
Writing & Preference Hy3 leads
Claude 3 Sonnet: 42.1 (#238), Hy3: 62.2 (#81)
| Benchmark | Claude 3 Sonnet | Hy3 |
|---|---|---|
| LMArena Text | 1218 | 1439 |
| LMArena Creative Writing | 1186 | 1402 |
| LMArena Multi-Turn | 1227 | 1436 |
Frequently asked questions
Is Claude 3 Sonnet better than Hy3?
Hy3 is the stronger model overall, scoring 44.2 to 29.0 on the Noometry Index.
Is Claude 3 Sonnet or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 29.6 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and Hy3 share?
17 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Hy3 has 19.