Model comparison
Llama 2-7B vs phi-3-medium 14B
Llama 2-7B and phi-3-medium 14B score almost the same on the Noometry Index (29.1 vs 29.7), so choose on price, context window or the category you care about most.
Last verified . 8 shared benchmarks.
Meta
MicrosoftSummary
- They share 8 benchmarks with published results for both. Llama 2-7B scores higher in 2 categories and phi-3-medium 14B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 2-7B leads 28.2 to 9.1.
Side by side
| Llama 2-7B | phi-3-medium 14B | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 29.1 | 29.7 |
| Released | 2023-07-18 | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 29 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
Llama 2-7B: 29.2 (#307), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Llama 2-7B | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1002 | — |
| BigCodeBench Complete | — | 48.7% |
Reasoning Not comparable
Llama 2-7B: 15.7 (#312), phi-3-medium 14B: —
| Benchmark | Llama 2-7B | phi-3-medium 14B |
|---|---|---|
| BIG-Bench Hard | 39.2% | 81.4% |
| Epoch Capabilities Index | 99.06 | 121.23 |
| HellaSwag | 77.2% | 82.4% |
| WinoGrande | 69.2% | 81.5% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1009 | — |
| Adversarial NLI | — | 55.8% |
| LAMBADA | 73.3% | — |
| PIQA | 78.8% | — |
Math Llama 2-7B leads
Llama 2-7B: 30.7 (#233), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Llama 2-7B | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1042 | — |
| MATH Level 5 | — | 17.6% |
| GSM8K | 16.7% | — |
Knowledge Llama 2-7B leads
Llama 2-7B: 28.2 (#248), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Llama 2-7B | phi-3-medium 14B |
|---|---|---|
| ARC (AI2) Challenge | 45.9% | 91.6% |
| MMLU | 45.8% | 78% |
| OpenBookQA | 58.6% | 87.4% |
| TriviaQA | 73.7% | 73.9% |
| GPQA Diamond | — | 27.6% |
| LMArena Expert | 1036 | — |
| BoolQ | 77.9% | — |
Multimodal Not comparable
Llama 2-7B: —, phi-3-medium 14B: —
| Benchmark | Llama 2-7B | phi-3-medium 14B |
|---|---|---|
| ScienceQA | 43.1% | — |
Multilingual Not comparable
Llama 2-7B: 23.8 (#293), phi-3-medium 14B: —
| Benchmark | Llama 2-7B | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 973 | — |
| LMArena Chinese | 973 | — |
| LMArena French | 970 | — |
| LMArena German | 978 | — |
| LMArena Russian | 995 | — |
| LMArena Spanish | 1007 | — |
Instruction Following Not comparable
Llama 2-7B: 50.8 (#298), phi-3-medium 14B: —
| Benchmark | Llama 2-7B | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1006 | — |
Long Context Not comparable
Llama 2-7B: 30.4 (#287), phi-3-medium 14B: —
| Benchmark | Llama 2-7B | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 999 | — |
Writing & Preference Not comparable
Llama 2-7B: 28.0 (#298), phi-3-medium 14B: —
| Benchmark | Llama 2-7B | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1053 | — |
| LMArena Creative Writing | 1033 | — |
| LMArena Multi-Turn | 1029 | — |
Frequently asked questions
Is Llama 2-7B better than phi-3-medium 14B?
Llama 2-7B and phi-3-medium 14B score almost the same on the Noometry Index (29.1 vs 29.7), so choose on price, context window or the category you care about most.
Is Llama 2-7B or phi-3-medium 14B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 29.2 in the Noometry coding category.
How many benchmarks do Llama 2-7B and phi-3-medium 14B share?
8 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and phi-3-medium 14B has 13.