Model comparison
Llama 2-7B vs Phi 3 Small 8k Instruct
Llama 2-7B and Phi 3 Small 8k Instruct score almost the same on the Noometry Index (29.1 vs 29.3), so choose on price, context window or the category you care about most.
Last verified . 22 shared benchmarks.
Meta
MicrosoftSummary
- They share 22 benchmarks with published results for both. Llama 2-7B scores higher in 3 categories and Phi 3 Small 8k Instruct in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Phi 3 Small 8k Instruct leads 28.5 to 23.8.
Side by side
| Llama 2-7B | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 29.1 | 29.3 |
| Released | 2023-07-18 | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 29 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 2-7B leads
Llama 2-7B: 29.2 (#307), Phi 3 Small 8k Instruct: 27.9 (#318)
| Benchmark | Llama 2-7B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1002 | 1101 |
| LiveBench Coding | — | 20.3% |
Reasoning Too close to call
Llama 2-7B: 15.7 (#312), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | Llama 2-7B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1009 | 1100 |
| BIG-Bench Hard | 39.2% | 79.1% |
| HellaSwag | 77.2% | 77% |
| WinoGrande | 69.2% | 81.5% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 15.9% |
| LiveBench Data Analysis | — | 30.3% |
| Adversarial NLI | — | 58.1% |
| Epoch Capabilities Index | 99.06 | — |
| LAMBADA | 73.3% | — |
| LiveBench | — | 24% |
| PIQA | 78.8% | — |
Math Llama 2-7B leads
Llama 2-7B: 30.7 (#233), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | Llama 2-7B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1042 | 1151 |
| LiveBench Math | — | 17.6% |
| GSM8K | 16.7% | — |
Knowledge Too close to call
Llama 2-7B: 28.2 (#248), Phi 3 Small 8k Instruct: 29.1 (#240)
| Benchmark | Llama 2-7B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1036 | 1067 |
| ARC (AI2) Challenge | 45.9% | 90.7% |
| MMLU | 45.8% | 75.7% |
| OpenBookQA | 58.6% | 88% |
| TriviaQA | 73.7% | 58.1% |
| BoolQ | 77.9% | — |
Multimodal Not comparable
Llama 2-7B: —, Phi 3 Small 8k Instruct: —
| Benchmark | Llama 2-7B | Phi 3 Small 8k Instruct |
|---|---|---|
| ScienceQA | 43.1% | — |
Multilingual Phi 3 Small 8k Instruct leads
Llama 2-7B: 23.8 (#293), Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | Llama 2-7B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 973 | 1058 |
| LMArena Chinese | 973 | 1061 |
| LMArena French | 970 | 1135 |
| LMArena German | 978 | 1080 |
| LMArena Russian | 995 | 1111 |
| LMArena Spanish | 1007 | 1111 |
| LMArena Japanese | — | 966 |
| LMArena Korean | — | 894 |
Instruction Following Phi 3 Small 8k Instruct leads
Llama 2-7B: 50.8 (#298), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | Llama 2-7B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1006 | 1087 |
| LiveBench Instruction Following | — | 47.2% |
Long Context Phi 3 Small 8k Instruct leads
Llama 2-7B: 30.4 (#287), Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | Llama 2-7B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 999 | 1088 |
Writing & Preference Phi 3 Small 8k Instruct leads
Llama 2-7B: 28.0 (#298), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | Llama 2-7B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1053 | 1110 |
| LMArena Creative Writing | 1033 | 1083 |
| LMArena Multi-Turn | 1029 | 1068 |
| LiveBench Language | — | 12.9% |
Frequently asked questions
Is Llama 2-7B better than Phi 3 Small 8k Instruct?
Llama 2-7B and Phi 3 Small 8k Instruct score almost the same on the Noometry Index (29.1 vs 29.3), so choose on price, context window or the category you care about most.
Is Llama 2-7B or Phi 3 Small 8k Instruct better for coding?
Llama 2-7B scores higher on coding benchmarks: 29.2 versus 27.9 in the Noometry coding category.
How many benchmarks do Llama 2-7B and Phi 3 Small 8k Instruct share?
22 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and Phi 3 Small 8k Instruct has 32.