Model comparison
Hy3 vs Llama 13b
Hy3 is the stronger model overall, scoring 44.2 to 24.4 on the Noometry Index.
Last verified . 8 shared benchmarks.
Tencent
MetaSummary
- They share 8 benchmarks with published results for both. Hy3 scores higher in 6 categories and Llama 13b in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.2 to 13.8.
Side by side
| Hy3 | Llama 13b | |
|---|---|---|
| Provider | Tencent | Meta |
| Noometry Index | 44.2 | 24.4 |
| Released | 2026-07-06 | 2023-02-24 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.0825 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 19 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Llama 13b: 21.4 (#337)
| Benchmark | Hy3 | Llama 13b |
|---|---|---|
| LMArena Coding | 1464 | 683 |
| LMArena WebDev | 1508 | — |
Reasoning Hy3 leads
Hy3: 26.1 (#136), Llama 13b: 14.0 (#329)
| Benchmark | Hy3 | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1447 | 728 |
| NYT Connections (extended) | 41.2% | — |
| BIG-Bench Hard | — | 37.9% |
| Epoch Capabilities Index | — | 100.58 |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |
Math Hy3 leads
Hy3: 40.1 (#93), Llama 13b: 26.7 (#256)
| Benchmark | Hy3 | Llama 13b |
|---|---|---|
| LMArena Math | 1475 | 838 |
| GSM8K | — | 20.6% |
Knowledge Not comparable
Hy3: 40.8 (#114), Llama 13b: —
| Benchmark | Hy3 | Llama 13b |
|---|---|---|
| LMArena Expert | 1460 | — |
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
Hy3: —, Llama 13b: —
| Benchmark | Hy3 | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Llama 13b: 16.6 (#297)
| Benchmark | Hy3 | Llama 13b |
|---|---|---|
| LMArena Non-English | 1426 | 819 |
| LMArena Chinese | 1493 | — |
| LMArena French | 1461 | — |
| LMArena German | 1439 | — |
| LMArena Japanese | 1392 | — |
| LMArena Korean | 1395 | — |
| LMArena Russian | 1432 | — |
| LMArena Spanish | 1456 | — |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Llama 13b: 36.7 (#305)
| Benchmark | Hy3 | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1426 | 781 |
Long Context Not comparable
Hy3: 44.1 (#75), Llama 13b: —
| Benchmark | Hy3 | Llama 13b |
|---|---|---|
| LMArena Longer Query | 1442 | — |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Llama 13b: 13.8 (#312)
| Benchmark | Hy3 | Llama 13b |
|---|---|---|
| LMArena Text | 1439 | 834 |
| LMArena Creative Writing | 1402 | 794 |
| LMArena Multi-Turn | 1436 | 753 |
Frequently asked questions
Is Hy3 better than Llama 13b?
Hy3 is the stronger model overall, scoring 44.2 to 24.4 on the Noometry Index.
Is Hy3 or Llama 13b better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 21.4 in the Noometry coding category.
How many benchmarks do Hy3 and Llama 13b share?
8 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Llama 13b has 21.