Model comparison
Llama 2-13B vs Phi 3 Medium 4k Instruct
Phi 3 Medium 4k Instruct is the stronger model overall, scoring 33.0 to 29.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
MicrosoftSummary
- They share 17 benchmarks with published results for both. Llama 2-13B scores higher in 0 categories and Phi 3 Medium 4k Instruct in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Phi 3 Medium 4k Instruct leads 21.7 to 12.8.
Side by side
| Llama 2-13B | Phi 3 Medium 4k Instruct | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 29.6 | 33.0 |
| Released | 2023-07-18 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 32 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi 3 Medium 4k Instruct leads
Llama 2-13B: 30.9 (#291), Phi 3 Medium 4k Instruct: 32.9 (#268)
| Benchmark | Llama 2-13B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1062 | 1130 |
Reasoning Phi 3 Medium 4k Instruct leads
Llama 2-13B: 12.8 (#337), Phi 3 Medium 4k Instruct: 21.7 (#214)
| Benchmark | Llama 2-13B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1051 | 1127 |
| Chess Puzzles | 0% | — |
| DTBench | 42.2% | — |
| BIG-Bench Hard | 58.2% | — |
| Epoch Capabilities Index | 106.17 | — |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |
Math Phi 3 Medium 4k Instruct leads
Llama 2-13B: 31.1 (#229), Phi 3 Medium 4k Instruct: 33.4 (#202)
| Benchmark | Llama 2-13B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1065 | 1173 |
| GSM8K | 36.9% | — |
Knowledge Phi 3 Medium 4k Instruct leads
Llama 2-13B: 28.1 (#249), Phi 3 Medium 4k Instruct: 30.2 (#229)
| Benchmark | Llama 2-13B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1030 | 1108 |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| MMLU | 55.6% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, Phi 3 Medium 4k Instruct: —
| Benchmark | Llama 2-13B | Phi 3 Medium 4k Instruct |
|---|---|---|
| ScienceQA | 55.8% | — |
Multilingual Phi 3 Medium 4k Instruct leads
Llama 2-13B: 26.5 (#279), Phi 3 Medium 4k Instruct: 30.6 (#263)
| Benchmark | Llama 2-13B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1024 | 1094 |
| LMArena Chinese | 1001 | 1108 |
| LMArena French | 1044 | 1110 |
| LMArena German | 1009 | 1101 |
| LMArena Japanese | 894 | 1042 |
| LMArena Korean | 953 | 954 |
| LMArena Russian | 1055 | 1145 |
| LMArena Spanish | 1087 | 1095 |
Instruction Following Phi 3 Medium 4k Instruct leads
Llama 2-13B: 53.3 (#287), Phi 3 Medium 4k Instruct: 57.6 (#268)
| Benchmark | Llama 2-13B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1045 | 1113 |
Long Context Phi 3 Medium 4k Instruct leads
Llama 2-13B: 32.3 (#269), Phi 3 Medium 4k Instruct: 34.0 (#255)
| Benchmark | Llama 2-13B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1064 | 1120 |
Writing & Preference Phi 3 Medium 4k Instruct leads
Llama 2-13B: 29.8 (#289), Phi 3 Medium 4k Instruct: 34.1 (#272)
| Benchmark | Llama 2-13B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1084 | 1138 |
| LMArena Creative Writing | 1047 | 1107 |
| LMArena Multi-Turn | 1050 | 1088 |
Frequently asked questions
Is Llama 2-13B better than Phi 3 Medium 4k Instruct?
Phi 3 Medium 4k Instruct is the stronger model overall, scoring 33.0 to 29.6 on the Noometry Index.
Is Llama 2-13B or Phi 3 Medium 4k Instruct better for coding?
Phi 3 Medium 4k Instruct scores higher on coding benchmarks: 32.9 versus 30.9 in the Noometry coding category.
How many benchmarks do Llama 2-13B and Phi 3 Medium 4k Instruct share?
17 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.