Model comparison
Codellama 70b Instruct vs Hy3
Hy3 is the stronger model overall, scoring 44.2 to 33.7 on the Noometry Index.
Last verified . 4 shared benchmarks.
Meta
TencentSummary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and Hy3 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.2 to 33.4.
Side by side
| Codellama 70b Instruct | Hy3 | |
|---|---|---|
| Provider | Meta | Tencent |
| Noometry Index | 33.7 | 44.2 |
| Released | — | 2026-07-06 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.0825 |
| Output $ / M tokens | — | $0.33 |
| Results tracked | 7 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Codellama 70b Instruct: 37.6 (#193), Hy3: 46.8 (#63)
| Benchmark | Codellama 70b Instruct | Hy3 |
|---|---|---|
| LMArena WebDev | — | 1508 |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1464 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning Hy3 leads
Codellama 70b Instruct: 20.1 (#242), Hy3: 26.1 (#136)
| Benchmark | Codellama 70b Instruct | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1447 |
| NYT Connections (extended) | — | 41.2% |
Math Not comparable
Codellama 70b Instruct: —, Hy3: 40.1 (#93)
| Benchmark | Codellama 70b Instruct | Hy3 |
|---|---|---|
| LMArena Math | — | 1475 |
Knowledge Not comparable
Codellama 70b Instruct: —, Hy3: 40.8 (#114)
| Benchmark | Codellama 70b Instruct | Hy3 |
|---|---|---|
| LMArena Expert | — | 1460 |
Multilingual Hy3 leads
Codellama 70b Instruct: 24.8 (#288), Hy3: 53.5 (#65)
| Benchmark | Codellama 70b Instruct | Hy3 |
|---|---|---|
| LMArena Non-English | 992 | 1426 |
| 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
Codellama 70b Instruct: 51.9 (#293), Hy3: 75.1 (#70)
| Benchmark | Codellama 70b Instruct | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1024 | 1426 |
Long Context Not comparable
Codellama 70b Instruct: —, Hy3: 44.1 (#75)
| Benchmark | Codellama 70b Instruct | Hy3 |
|---|---|---|
| LMArena Longer Query | — | 1442 |
Writing & Preference Hy3 leads
Codellama 70b Instruct: 33.4 (#277), Hy3: 62.2 (#81)
| Benchmark | Codellama 70b Instruct | Hy3 |
|---|---|---|
| LMArena Text | 1057 | 1439 |
| LMArena Creative Writing | — | 1402 |
| LMArena Multi-Turn | — | 1436 |
Frequently asked questions
Is Codellama 70b Instruct better than Hy3?
Hy3 is the stronger model overall, scoring 44.2 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 37.6 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Hy3 share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Hy3 has 19.