Model comparison
Hy3 vs Llama 3-8B
Hy3 is the stronger model overall, scoring 44.2 to 25.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Tencent
MetaSummary
- They share 17 benchmarks with published results for both. Hy3 scores higher in 8 categories and Llama 3-8B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Hy3 leads 40.8 to 7.8.
Side by side
| Hy3 | Llama 3-8B | |
|---|---|---|
| Provider | Tencent | Meta |
| Noometry Index | 44.2 | 25.5 |
| Released | 2026-07-06 | 2024-04-18 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.0825 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 19 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Llama 3-8B: 31.0 (#289)
| Benchmark | Hy3 | Llama 3-8B |
|---|---|---|
| LMArena Coding | 1464 | 1152 |
| LMArena WebDev | 1508 | — |
| BigCodeBench Instruct | — | 31.9% |
| BigCodeBench Complete | — | 36.9% |
| HumanEval+ | — | 56.7% |
| MBPP+ | — | 54.8% |
Reasoning Hy3 leads
Hy3: 26.1 (#136), Llama 3-8B: 14.3 (#326)
| Benchmark | Hy3 | Llama 3-8B |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1133 |
| NYT Connections (extended) | 41.2% | — |
| Chess Puzzles | — | 0% |
| DTBench | — | 43.9% |
| Adversarial NLI | — | 57.3% |
| Epoch Capabilities Index | — | 116.45 |
| ForecastBench | — | 58.6 |
| WinoGrande | — | 75.7% |
Math Hy3 leads
Hy3: 40.1 (#93), Llama 3-8B: 8.8 (#323)
| Benchmark | Hy3 | Llama 3-8B |
|---|---|---|
| LMArena Math | 1475 | 1151 |
| OTIS Mock AIME 2024-2025 | — | 1.9% |
| MATH Level 5 | — | 6.1% |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Llama 3-8B: 7.8 (#308)
| Benchmark | Hy3 | Llama 3-8B |
|---|---|---|
| LMArena Expert | 1460 | 1113 |
| GPQA Diamond | — | 26.1% |
| ARC (AI2) Challenge | — | 82.8% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 82.6% |
| TriviaQA | — | 67.7% |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Llama 3-8B: 30.8 (#261)
| Benchmark | Hy3 | Llama 3-8B |
|---|---|---|
| LMArena Non-English | 1426 | 1098 |
| LMArena Chinese | 1493 | 1076 |
| LMArena French | 1461 | 1159 |
| LMArena German | 1439 | 1104 |
| LMArena Japanese | 1392 | 967 |
| LMArena Korean | 1395 | 1004 |
| LMArena Russian | 1432 | 1109 |
| LMArena Spanish | 1456 | 1173 |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Llama 3-8B: 58.4 (#260)
| Benchmark | Hy3 | Llama 3-8B |
|---|---|---|
| LMArena Instruction Following | 1426 | 1127 |
Long Context Hy3 leads
Hy3: 44.1 (#75), Llama 3-8B: 34.2 (#251)
| Benchmark | Hy3 | Llama 3-8B |
|---|---|---|
| LMArena Longer Query | 1442 | 1128 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Llama 3-8B: 37.5 (#256)
| Benchmark | Hy3 | Llama 3-8B |
|---|---|---|
| LMArena Text | 1439 | 1166 |
| LMArena Creative Writing | 1402 | 1150 |
| LMArena Multi-Turn | 1436 | 1152 |
Frequently asked questions
Is Hy3 better than Llama 3-8B?
Hy3 is the stronger model overall, scoring 44.2 to 25.5 on the Noometry Index.
Is Hy3 or Llama 3-8B better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 31.0 in the Noometry coding category.
How many benchmarks do Hy3 and Llama 3-8B share?
17 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Llama 3-8B has 34.