Model comparison
Hy3 vs Llama 3.2 3B
Hy3 is the stronger model overall, scoring 44.2 to 28.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
Summary
- They share 13 benchmarks with published results for both. Hy3 scores higher in 8 categories and Llama 3.2 3B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.2 to 24.7.
- Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $0.0825 / $0.33 for Hy3.
- Hy3 accepts more context: 262K tokens versus 131K.
Side by side
| Hy3 | Llama 3.2 3B | |
|---|---|---|
| Provider | Tencent | Meta |
| Noometry Index | 44.2 | 28.9 |
| Released | 2026-07-06 | 2024-09-24 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 128K | 118K |
| Input $ / M tokens | $0.0825 | $0.05 |
| Output $ / M tokens | $0.33 | $0.33 |
| Results tracked | 19 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Llama 3.2 3B: 27.6 (#319)
| Benchmark | Hy3 | Llama 3.2 3B |
|---|---|---|
| LMArena Coding | 1464 | 1098 |
| LMArena WebDev | 1508 | — |
| BigCodeBench Instruct | — | 23.4% |
| BigCodeBench Complete | — | 28.3% |
Agentic & Tool Use Not comparable
Hy3: —, Llama 3.2 3B: 20.1 (#143)
| Benchmark | Hy3 | Llama 3.2 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 21.9% |
| BALROG | — | 10.1% |
Reasoning Hy3 leads
Hy3: 26.1 (#136), Llama 3.2 3B: 21.0 (#228)
| Benchmark | Hy3 | Llama 3.2 3B |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1095 |
| NYT Connections (extended) | 41.2% | — |
Math Hy3 leads
Hy3: 40.1 (#93), Llama 3.2 3B: 32.4 (#214)
| Benchmark | Hy3 | Llama 3.2 3B |
|---|---|---|
| LMArena Math | 1475 | 1126 |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Llama 3.2 3B: 29.7 (#235)
| Benchmark | Hy3 | Llama 3.2 3B |
|---|---|---|
| LMArena Expert | 1460 | 1090 |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Llama 3.2 3B: 26.2 (#281)
| Benchmark | Hy3 | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | 1426 | 1019 |
| LMArena Chinese | 1493 | 1017 |
| LMArena German | 1439 | 1056 |
| LMArena Russian | 1432 | 949 |
| LMArena French | 1461 | — |
| LMArena Japanese | 1392 | — |
| LMArena Korean | 1395 | — |
| LMArena Spanish | 1456 | — |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Llama 3.2 3B: 56.0 (#275)
| Benchmark | Hy3 | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | 1426 | 1089 |
Long Context Hy3 leads
Hy3: 44.1 (#75), Llama 3.2 3B: 33.4 (#261)
| Benchmark | Hy3 | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | 1442 | 1100 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Llama 3.2 3B: 24.7 (#307)
| Benchmark | Hy3 | Llama 3.2 3B |
|---|---|---|
| LMArena Text | 1439 | 1110 |
| LMArena Creative Writing | 1402 | 1094 |
| LMArena Multi-Turn | 1436 | 1105 |
| EQ-Bench Creative Writing | — | 595 |
Frequently asked questions
Is Hy3 better than Llama 3.2 3B?
Hy3 is the stronger model overall, scoring 44.2 to 28.9 on the Noometry Index.
Which is cheaper, Hy3 or Llama 3.2 3B?
Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; Hy3 lists at $0.0825 and $0.33.
Is Hy3 or Llama 3.2 3B better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 27.6 in the Noometry coding category.
Which has the bigger context window?
Hy3 does, with 262K tokens against 131K.
How many benchmarks do Hy3 and Llama 3.2 3B share?
13 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Llama 3.2 3B has 18.