Model comparison
Claude 3 Opus vs Hy3
Hy3 is the stronger model overall, scoring 44.2 to 29.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
TencentSummary
- They share 17 benchmarks with published results for both. Claude 3 Opus 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 14.8.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Opus | Hy3 | |
|---|---|---|
| Provider | Anthropic | Tencent |
| Noometry Index | 29.5 | 44.2 |
| Released | 2024-02-29 | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.13 |
| Output $ / M tokens | — | $0.53 |
| Results tracked | 46 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Claude 3 Opus: 32.9 (#267), Hy3: 46.8 (#63)
| Benchmark | Claude 3 Opus | Hy3 |
|---|---|---|
| LMArena Coding | 1264 | 1464 |
| LMArena WebDev | — | 1508 |
| WeirdML | 19.2% | — |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
Claude 3 Opus: 24.6 (#116), Hy3: —
| Benchmark | Claude 3 Opus | Hy3 |
|---|---|---|
| Cybench | 10% | — |
| METR Time Horizons | 29.5% | — |
Reasoning Hy3 leads
Claude 3 Opus: 14.6 (#324), Hy3: 26.1 (#136)
| Benchmark | Claude 3 Opus | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1245 | 1447 |
| SimpleBench | 23.5% | — |
| NYT Connections (extended) | — | 41.2% |
| Chess Puzzles | 5% | — |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 40.6% | — |
| DTBench | 61.6% | — |
| LiveBench Data Analysis | 57.9% | — |
| LMCA | 17% | — |
| Epoch Capabilities Index | 126.91 | — |
| ForecastBench | 58.4 | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Hy3 leads
Claude 3 Opus: 14.8 (#299), Hy3: 40.1 (#93)
| Benchmark | Claude 3 Opus | Hy3 |
|---|---|---|
| LMArena Math | 1273 | 1475 |
| OTIS Mock AIME 2024-2025 | 4.7% | — |
| LiveBench Math | 43.6% | — |
| MATH Level 5 | 37.5% | — |
Knowledge Hy3 leads
Claude 3 Opus: 24.5 (#267), Hy3: 40.8 (#114)
| Benchmark | Claude 3 Opus | Hy3 |
|---|---|---|
| LMArena Expert | 1223 | 1460 |
| GPQA Diamond | 47.2% | — |
| SimpleQA Verified | 12.6% | — |
| Confabulations | 22.7% | — |
| MMLU | 84.6% | — |
Multimodal Not comparable
Claude 3 Opus: 27.1 (#116), Hy3: —
| Benchmark | Claude 3 Opus | Hy3 |
|---|---|---|
| LMArena Vision | 1023 | — |
Multilingual Hy3 leads
Claude 3 Opus: 41.4 (#207), Hy3: 53.5 (#65)
| Benchmark | Claude 3 Opus | Hy3 |
|---|---|---|
| LMArena Non-English | 1258 | 1426 |
| LMArena Chinese | 1248 | 1493 |
| LMArena French | 1275 | 1461 |
| LMArena German | 1258 | 1439 |
| LMArena Japanese | 1204 | 1392 |
| LMArena Korean | 1187 | 1395 |
| LMArena Russian | 1280 | 1432 |
| LMArena Spanish | 1246 | 1456 |
Instruction Following Hy3 leads
Claude 3 Opus: 64.1 (#228), Hy3: 75.1 (#70)
| Benchmark | Claude 3 Opus | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1426 |
| LiveBench Instruction Following | 63.9% | — |
Long Context Hy3 leads
Claude 3 Opus: 38.2 (#202), Hy3: 44.1 (#75)
| Benchmark | Claude 3 Opus | Hy3 |
|---|---|---|
| LMArena Longer Query | 1259 | 1442 |
Writing & Preference Hy3 leads
Claude 3 Opus: 47.2 (#213), Hy3: 62.2 (#81)
| Benchmark | Claude 3 Opus | Hy3 |
|---|---|---|
| LMArena Text | 1262 | 1439 |
| LMArena Creative Writing | 1235 | 1402 |
| LMArena Multi-Turn | 1275 | 1436 |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Hy3?
Hy3 is the stronger model overall, scoring 44.2 to 29.5 on the Noometry Index.
Is Claude 3 Opus or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Hy3 share?
17 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Hy3 has 19.