Model comparison
Hy4 preview vs Llama 13b
Hy4 preview is the stronger model overall, scoring 45.3 to 24.4 on the Noometry Index.
Last verified . 0 shared benchmarks.
Tencent
MetaSummary
- The widest gap is in coding, where Hy4 preview leads 51.6 to 21.4.
Side by side
| Hy4 preview | Llama 13b | |
|---|---|---|
| Provider | Tencent | Meta |
| Noometry Index | 45.3 | 24.4 |
| Released | 2026-08-28 | 2023-02-24 |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.83 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 3 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Hy4 preview: 51.6 (#38), Llama 13b: 21.4 (#337)
| Benchmark | Hy4 preview | Llama 13b |
|---|---|---|
| LMArena WebDev | 1632 | — |
| LMArena Coding | — | 683 |
Reasoning Hy4 preview leads
Hy4 preview: 31.9 (#79), Llama 13b: 14.0 (#329)
| Benchmark | Hy4 preview | Llama 13b |
|---|---|---|
| NYT Connections (extended) | 68.2% | — |
| LMArena Hard Prompts | — | 728 |
| BIG-Bench Hard | — | 37.9% |
| Epoch Capabilities Index | — | 100.58 |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), Llama 13b: 26.7 (#256)
| Benchmark | Hy4 preview | Llama 13b |
|---|---|---|
| ProofBench | 75% | — |
| LMArena Math | — | 838 |
| GSM8K | — | 20.6% |
Knowledge Not comparable
Hy4 preview: —, Llama 13b: —
| Benchmark | Hy4 preview | Llama 13b |
|---|---|---|
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
Hy4 preview: —, Llama 13b: —
| Benchmark | Hy4 preview | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |
Multilingual Not comparable
Hy4 preview: —, Llama 13b: 16.6 (#297)
| Benchmark | Hy4 preview | Llama 13b |
|---|---|---|
| LMArena Non-English | — | 819 |
Instruction Following Not comparable
Hy4 preview: —, Llama 13b: 36.7 (#305)
| Benchmark | Hy4 preview | Llama 13b |
|---|---|---|
| LMArena Instruction Following | — | 781 |
Writing & Preference Not comparable
Hy4 preview: —, Llama 13b: 13.8 (#312)
| Benchmark | Hy4 preview | Llama 13b |
|---|---|---|
| LMArena Text | — | 834 |
| LMArena Creative Writing | — | 794 |
| LMArena Multi-Turn | — | 753 |
Frequently asked questions
Is Hy4 preview better than Llama 13b?
Hy4 preview is the stronger model overall, scoring 45.3 to 24.4 on the Noometry Index.
Is Hy4 preview or Llama 13b better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 21.4 in the Noometry coding category.
How many benchmarks do Hy4 preview and Llama 13b share?
0 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Llama 13b has 21.