Model comparison
Hy3 vs Llama 2-13B
Hy3 is the stronger model overall, scoring 43.6 to 29.1 on the Noometry Index.
Last verified . 15 shared benchmarks.
Tencent
MetaSummary
- They share 15 benchmarks with published results for both. Hy3 scores higher in 8 categories and Llama 2-13B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.5 to 30.0.
Side by side
| Hy3 | Llama 2-13B | |
|---|---|---|
| Provider | Tencent | Meta |
| Noometry Index | 43.6 | 29.1 |
| Released | 2026-07-06 | 2023-07-18 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.13 | — |
| Output $ / M tokens | $0.53 | — |
| Results tracked | 17 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.6 (#60), Llama 2-13B: 30.4 (#287)
| Benchmark | Hy3 | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1465 | 1062 |
| LMArena WebDev | 1509 | — |
Reasoning Hy3 leads
Hy3: 25.0 (#134), Llama 2-13B: 12.3 (#333)
| Benchmark | Hy3 | Llama 2-13B |
|---|---|---|
| LMArena Hard Prompts | 1449 | 1051 |
| NYT Connections (extended) | 41.2% | — |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.2% |
| BIG-Bench Hard | — | 58.2% |
| Epoch Capabilities Index | — | 105.8 |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math Hy3 leads
Hy3: 37.4 (#98), Llama 2-13B: 28.7 (#226)
| Benchmark | Hy3 | Llama 2-13B |
|---|---|---|
| LMArena Math | 1475 | 1065 |
| GSM8K | — | 36.9% |
Knowledge Hy3 leads
Hy3: 40.2 (#108), Llama 2-13B: 27.5 (#244)
| Benchmark | Hy3 | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1461 | 1030 |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
Hy3: —, Llama 2-13B: —
| Benchmark | Hy3 | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |
Multilingual Hy3 leads
Hy3: 53.7 (#60), Llama 2-13B: 26.7 (#274)
| Benchmark | Hy3 | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1427 | 1024 |
| LMArena Chinese | 1496 | 1001 |
| LMArena French | 1461 | 1043 |
| LMArena Korean | 1390 | 953 |
| LMArena Russian | 1435 | 1055 |
| LMArena Spanish | 1448 | 1086 |
| LMArena German | — | 1009 |
| LMArena Japanese | — | 894 |
Instruction Following Hy3 leads
Hy3: 75.3 (#68), Llama 2-13B: 53.5 (#282)
| Benchmark | Hy3 | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1425 | 1046 |
Long Context Hy3 leads
Hy3: 44.1 (#70), Llama 2-13B: 32.3 (#264)
| Benchmark | Hy3 | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1443 | 1064 |
Writing & Preference Hy3 leads
Hy3: 62.5 (#75), Llama 2-13B: 30.0 (#284)
| Benchmark | Hy3 | Llama 2-13B |
|---|---|---|
| LMArena Text | 1442 | 1085 |
| LMArena Creative Writing | 1399 | 1047 |
| LMArena Multi-Turn | 1436 | 1050 |
Frequently asked questions
Is Hy3 better than Llama 2-13B?
Hy3 is the stronger model overall, scoring 43.6 to 29.1 on the Noometry Index.
Is Hy3 or Llama 2-13B better for coding?
Hy3 scores higher on coding benchmarks: 46.6 versus 30.4 in the Noometry coding category.
How many benchmarks do Hy3 and Llama 2-13B share?
15 benchmarks have published results for both models. Hy3 has 17 scored results on Noometry and Llama 2-13B has 32.