Model comparison
Llama 3-8B vs Phi 3 Mini 128k Instruct
Phi 3 Mini 128k Instruct is the stronger model overall, scoring 29.7 to 25.5 on the Noometry Index.
Last verified . 19 shared benchmarks.
Meta
MicrosoftSummary
- They share 19 benchmarks with published results for both. Llama 3-8B scores higher in 5 categories and Phi 3 Mini 128k Instruct in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Phi 3 Mini 128k Instruct leads 31.6 to 8.8.
Side by side
| Llama 3-8B | Phi 3 Mini 128k Instruct | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 25.5 | 29.7 |
| Released | 2024-04-18 | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 34 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-8B leads
Llama 3-8B: 31.0 (#289), Phi 3 Mini 128k Instruct: 28.8 (#312)
| Benchmark | Llama 3-8B | Phi 3 Mini 128k Instruct |
|---|---|---|
| BigCodeBench Instruct | 31.9% | 29.6% |
| LMArena Coding | 1152 | 1039 |
| BigCodeBench Complete | 36.9% | 40.6% |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Phi 3 Mini 128k Instruct leads
Llama 3-8B: 14.3 (#326), Phi 3 Mini 128k Instruct: 19.6 (#256)
| Benchmark | Llama 3-8B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1028 |
| Chess Puzzles | 0% | — |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.45 | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Phi 3 Mini 128k Instruct leads
Llama 3-8B: 8.8 (#323), Phi 3 Mini 128k Instruct: 31.6 (#222)
| Benchmark | Llama 3-8B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1151 | 1089 |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| MATH Level 5 | 6.1% | — |
Knowledge Phi 3 Mini 128k Instruct leads
Llama 3-8B: 7.8 (#308), Phi 3 Mini 128k Instruct: 26.8 (#254)
| Benchmark | Llama 3-8B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1113 | 984 |
| GPQA Diamond | 26.1% | — |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual Llama 3-8B leads
Llama 3-8B: 30.8 (#261), Phi 3 Mini 128k Instruct: 25.2 (#285)
| Benchmark | Llama 3-8B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1098 | 1000 |
| LMArena Chinese | 1076 | 1016 |
| LMArena French | 1159 | 1039 |
| LMArena German | 1104 | 1006 |
| LMArena Japanese | 967 | 899 |
| LMArena Korean | 1004 | 856 |
| LMArena Russian | 1109 | 1004 |
| LMArena Spanish | 1173 | 1059 |
Instruction Following Llama 3-8B leads
Llama 3-8B: 58.4 (#260), Phi 3 Mini 128k Instruct: 51.8 (#294)
| Benchmark | Llama 3-8B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1127 | 1023 |
Long Context Llama 3-8B leads
Llama 3-8B: 34.2 (#251), Phi 3 Mini 128k Instruct: 30.4 (#289)
| Benchmark | Llama 3-8B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1128 | 996 |
Writing & Preference Llama 3-8B leads
Llama 3-8B: 37.5 (#256), Phi 3 Mini 128k Instruct: 27.1 (#301)
| Benchmark | Llama 3-8B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1166 | 1050 |
| LMArena Creative Writing | 1150 | 1024 |
| LMArena Multi-Turn | 1152 | 989 |
Frequently asked questions
Is Llama 3-8B better than Phi 3 Mini 128k Instruct?
Phi 3 Mini 128k Instruct is the stronger model overall, scoring 29.7 to 25.5 on the Noometry Index.
Is Llama 3-8B or Phi 3 Mini 128k Instruct better for coding?
Llama 3-8B scores higher on coding benchmarks: 31.0 versus 28.8 in the Noometry coding category.
How many benchmarks do Llama 3-8B and Phi 3 Mini 128k Instruct share?
19 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.