Model comparison
Llama 3.2 3B vs Phi-2
Llama 3.2 3B has enough public results to be ranked (#318); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Meta
MicrosoftSide by side
| Llama 3.2 3B | Phi-2 | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 28.4 | — |
| Released | 2024-09-24 | 2023-12-12 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 118K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 18 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 3B: 27.1 (#314), Phi-2: —
| Benchmark | Llama 3.2 3B | Phi-2 |
|---|---|---|
| BigCodeBench Instruct | 23.4% | — |
| LMArena Coding | 1098 | — |
| BigCodeBench Complete | 28.3% | — |
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
Llama 3.2 3B: 19.9 (#135), Phi-2: —
| Benchmark | Llama 3.2 3B | Phi-2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |
Reasoning Not comparable
Llama 3.2 3B: 20.1 (#225), Phi-2: —
| Benchmark | Llama 3.2 3B | Phi-2 |
|---|---|---|
| LMArena Hard Prompts | 1095 | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| Epoch Capabilities Index | — | 107.62 |
| HellaSwag | — | 53.6% |
| WinoGrande | — | 54.7% |
Math Not comparable
Llama 3.2 3B: 29.9 (#213), Phi-2: —
| Benchmark | Llama 3.2 3B | Phi-2 |
|---|---|---|
| LMArena Math | 1126 | — |
Knowledge Not comparable
Llama 3.2 3B: 29.1 (#232), Phi-2: —
| Benchmark | Llama 3.2 3B | Phi-2 |
|---|---|---|
| LMArena Expert | 1090 | — |
| ARC (AI2) Challenge | — | 75.9% |
| MMLU | — | 58.4% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |
Multilingual Not comparable
Llama 3.2 3B: 26.4 (#276), Phi-2: —
| Benchmark | Llama 3.2 3B | Phi-2 |
|---|---|---|
| LMArena Non-English | 1019 | — |
| LMArena Chinese | 1017 | — |
| LMArena German | 1056 | — |
| LMArena Russian | 949 | — |
Instruction Following Not comparable
Llama 3.2 3B: 56.3 (#270), Phi-2: —
| Benchmark | Llama 3.2 3B | Phi-2 |
|---|---|---|
| LMArena Instruction Following | 1089 | — |
Long Context Not comparable
Llama 3.2 3B: 33.4 (#256), Phi-2: —
| Benchmark | Llama 3.2 3B | Phi-2 |
|---|---|---|
| LMArena Longer Query | 1101 | — |
Writing & Preference Not comparable
Llama 3.2 3B: 24.9 (#302), Phi-2: —
| Benchmark | Llama 3.2 3B | Phi-2 |
|---|---|---|
| LMArena Text | 1110 | — |
| LMArena Creative Writing | 1094 | — |
| EQ-Bench Creative Writing | 595 | — |
| LMArena Multi-Turn | 1105 | — |
Frequently asked questions
Is Llama 3.2 3B better than Phi-2?
Llama 3.2 3B has enough public results to be ranked (#318); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do Llama 3.2 3B and Phi-2 share?
0 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Phi-2 has 11.