Model comparison
Llama 13b vs Phi-2
Llama 13b has enough public results to be ranked (#344); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 8 shared benchmarks.
Meta
MicrosoftSummary
- They share 8 benchmarks with published results for both.
Side by side
| Llama 13b | Phi-2 | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 23.9 | — |
| Released | 2023-02-24 | 2023-12-12 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 13b: 20.9 (#332), Phi-2: —
| Benchmark | Llama 13b | Phi-2 |
|---|---|---|
| LMArena Coding | 683 | — |
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |
Reasoning Not comparable
Llama 13b: 13.4 (#327), Phi-2: —
| Benchmark | Llama 13b | Phi-2 |
|---|---|---|
| BIG-Bench Hard | 37.9% | 59.4% |
| Epoch Capabilities Index | 100.09 | 107.62 |
| HellaSwag | 79.2% | 53.6% |
| WinoGrande | 73% | 54.7% |
| LMArena Hard Prompts | 728 | — |
| Adversarial NLI | — | 42.5% |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
Math Not comparable
Llama 13b: 24.4 (#259), Phi-2: —
| Benchmark | Llama 13b | Phi-2 |
|---|---|---|
| LMArena Math | 838 | — |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, Phi-2: —
| Benchmark | Llama 13b | Phi-2 |
|---|---|---|
| ARC (AI2) Challenge | 52.7% | 75.9% |
| MMLU | 47.7% | 58.4% |
| OpenBookQA | 56.4% | 73.6% |
| TriviaQA | 77.9% | 45.2% |
| BoolQ | 78.7% | — |
Multimodal Not comparable
Llama 13b: —, Phi-2: —
| Benchmark | Llama 13b | Phi-2 |
|---|---|---|
| ScienceQA | 43.3% | — |
Multilingual Not comparable
Llama 13b: 16.8 (#292), Phi-2: —
| Benchmark | Llama 13b | Phi-2 |
|---|---|---|
| LMArena Non-English | 819 | — |
Instruction Following Not comparable
Llama 13b: 36.9 (#300), Phi-2: —
| Benchmark | Llama 13b | Phi-2 |
|---|---|---|
| LMArena Instruction Following | 781 | — |
Writing & Preference Not comparable
Llama 13b: 13.9 (#307), Phi-2: —
| Benchmark | Llama 13b | Phi-2 |
|---|---|---|
| LMArena Text | 834 | — |
| LMArena Creative Writing | 794 | — |
| LMArena Multi-Turn | 753 | — |
Frequently asked questions
Is Llama 13b better than Phi-2?
Llama 13b has enough public results to be ranked (#344); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do Llama 13b and Phi-2 share?
8 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Phi-2 has 11.