Model comparison
Claude 3.5 Sonnet vs Hy3
Hy3 is the stronger model overall, scoring 44.2 to 34.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
TencentSummary
- They share 17 benchmarks with published results for both. Claude 3.5 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 19.2.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Sonnet | Hy3 | |
|---|---|---|
| Provider | Anthropic | Tencent |
| Noometry Index | 34.6 | 44.2 |
| Released | 2024-06-20 | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.0825 |
| Output $ / M tokens | — | $0.33 |
| Results tracked | 60 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Claude 3.5 Sonnet: 39.0 (#165), Hy3: 46.8 (#63)
| Benchmark | Claude 3.5 Sonnet | Hy3 |
|---|---|---|
| LMArena Coding | 1342 | 1464 |
| Aider Polyglot | 51.6% | — |
| LMArena WebDev | — | 1508 |
| GSO | 4.6% | — |
| WeirdML | 40% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Sonnet: 32.3 (#67), Hy3: —
| Benchmark | Claude 3.5 Sonnet | Hy3 |
|---|---|---|
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning Hy3 leads
Claude 3.5 Sonnet: 23.1 (#183), Hy3: 26.1 (#136)
| Benchmark | Claude 3.5 Sonnet | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1447 |
| SimpleBench | 41.4% | — |
| NYT Connections (extended) | — | 41.2% |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| DTBench | 67.8% | — |
| LiveBench Data Analysis | 55% | — |
| Epoch Capabilities Index | 133.55 | — |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math Hy3 leads
Claude 3.5 Sonnet: 19.2 (#288), Hy3: 40.1 (#93)
| Benchmark | Claude 3.5 Sonnet | Hy3 |
|---|---|---|
| LMArena Math | 1307 | 1475 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Hy3 leads
Claude 3.5 Sonnet: 28.6 (#245), Hy3: 40.8 (#114)
| Benchmark | Claude 3.5 Sonnet | Hy3 |
|---|---|---|
| LMArena Expert | 1265 | 1460 |
| GPQA Diamond | 55.3% | — |
| Humanity's Last Exam | 4.1% | — |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal Not comparable
Claude 3.5 Sonnet: 26.5 (#120), Hy3: —
| Benchmark | Claude 3.5 Sonnet | Hy3 |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual Hy3 leads
Claude 3.5 Sonnet: 43.2 (#185), Hy3: 53.5 (#65)
| Benchmark | Claude 3.5 Sonnet | Hy3 |
|---|---|---|
| LMArena Non-English | 1283 | 1426 |
| LMArena Chinese | 1272 | 1493 |
| LMArena French | 1305 | 1461 |
| LMArena German | 1297 | 1439 |
| LMArena Japanese | 1234 | 1392 |
| LMArena Korean | 1200 | 1395 |
| LMArena Russian | 1306 | 1432 |
| LMArena Spanish | 1290 | 1456 |
Instruction Following Hy3 leads
Claude 3.5 Sonnet: 68.8 (#182), Hy3: 75.1 (#70)
| Benchmark | Claude 3.5 Sonnet | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1297 | 1426 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context Hy3 leads
Claude 3.5 Sonnet: 39.9 (#167), Hy3: 44.1 (#75)
| Benchmark | Claude 3.5 Sonnet | Hy3 |
|---|---|---|
| LMArena Longer Query | 1311 | 1442 |
Writing & Preference Hy3 leads
Claude 3.5 Sonnet: 52.9 (#164), Hy3: 62.2 (#81)
| Benchmark | Claude 3.5 Sonnet | Hy3 |
|---|---|---|
| LMArena Text | 1298 | 1439 |
| LMArena Creative Writing | 1292 | 1402 |
| LMArena Multi-Turn | 1326 | 1436 |
| Short-Story Creative Writing | 80.3% | — |
| EQ-Bench Creative Writing | 1451 | — |
| WildBench | 79.2% | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Hy3?
Hy3 is the stronger model overall, scoring 44.2 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 39.0 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Hy3 share?
17 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Hy3 has 19.