Model comparison
Llama 3.2 1B vs Phi-2
Llama 3.2 1B has enough public results to be ranked (#354); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
Meta
MicrosoftSummary
- They share 1 benchmark with published results for both.
Side by side
| Llama 3.2 1B | Phi-2 | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 20.1 | — |
| Released | 2024-09-24 | 2023-12-12 |
| Weights | Open | Open |
| Context window | 60K | — |
| Max output | 54K | — |
| Input $ / M tokens | $0.027 | — |
| Output $ / M tokens | $0.20 | — |
| Results tracked | 22 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 1B: 21.1 (#338), Phi-2: —
| Benchmark | Llama 3.2 1B | Phi-2 |
|---|---|---|
| BigCodeBench Instruct | 8.2% | — |
| LMArena Coding | 1070 | — |
| BigCodeBench Complete | 11.3% | — |
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
Llama 3.2 1B: 14.6 (#150), Phi-2: —
| Benchmark | Llama 3.2 1B | Phi-2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 10.8% | — |
| BALROG | 6.6% | — |
Reasoning Not comparable
Llama 3.2 1B: 16.2 (#308), Phi-2: —
| Benchmark | Llama 3.2 1B | Phi-2 |
|---|---|---|
| Epoch Capabilities Index | 101.99 | 107.94 |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1044 | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| HellaSwag | — | 53.6% |
| WinoGrande | — | 54.7% |
Math Not comparable
Llama 3.2 1B: 10.4 (#313), Phi-2: —
| Benchmark | Llama 3.2 1B | Phi-2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| LMArena Math | 1086 | — |
Knowledge Not comparable
Llama 3.2 1B: 7.2 (#312), Phi-2: —
| Benchmark | Llama 3.2 1B | Phi-2 |
|---|---|---|
| GPQA Diamond | 23.9% | — |
| LMArena Expert | 1007 | — |
| ARC (AI2) Challenge | — | 75.9% |
| MMLU | — | 58.4% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |
Multilingual Not comparable
Llama 3.2 1B: 23.8 (#292), Phi-2: —
| Benchmark | Llama 3.2 1B | Phi-2 |
|---|---|---|
| LMArena Non-English | 973 | — |
| LMArena Chinese | 959 | — |
| LMArena German | 1014 | — |
| LMArena Russian | 941 | — |
Instruction Following Not comparable
Llama 3.2 1B: 52.4 (#290), Phi-2: —
| Benchmark | Llama 3.2 1B | Phi-2 |
|---|---|---|
| LMArena Instruction Following | 1031 | — |
Long Context Not comparable
Llama 3.2 1B: 31.9 (#274), Phi-2: —
| Benchmark | Llama 3.2 1B | Phi-2 |
|---|---|---|
| LMArena Longer Query | 1050 | — |
Writing & Preference Not comparable
Llama 3.2 1B: 21.3 (#310), Phi-2: —
| Benchmark | Llama 3.2 1B | Phi-2 |
|---|---|---|
| LMArena Text | 1055 | — |
| LMArena Creative Writing | 1033 | — |
| EQ-Bench Creative Writing | 200 | — |
| LMArena Multi-Turn | 1030 | — |
Frequently asked questions
Is Llama 3.2 1B better than Phi-2?
Llama 3.2 1B has enough public results to be ranked (#354); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do Llama 3.2 1B and Phi-2 share?
1 benchmark has published results for both models. Llama 3.2 1B has 22 scored results on Noometry and Phi-2 has 11.