Model comparison
Llama 3.2 3B vs Phi 3 Medium 4k Instruct
Phi 3 Medium 4k Instruct is the stronger model overall, scoring 32.4 to 28.4 on the Noometry Index.
Last verified . 13 shared benchmarks.
Meta
MicrosoftSummary
- They share 13 benchmarks with published results for both. Llama 3.2 3B scores higher in 0 categories and Phi 3 Medium 4k Instruct in 8 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Phi 3 Medium 4k Instruct leads 34.3 to 24.9.
Side by side
| Llama 3.2 3B | Phi 3 Medium 4k Instruct | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 28.4 | 32.4 |
| Released | 2024-09-24 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 118K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 18 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi 3 Medium 4k Instruct leads
Llama 3.2 3B: 27.1 (#314), Phi 3 Medium 4k Instruct: 32.3 (#263)
| Benchmark | Llama 3.2 3B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1098 | 1130 |
| BigCodeBench Instruct | 23.4% | — |
| BigCodeBench Complete | 28.3% | — |
Agentic & Tool Use Not comparable
Llama 3.2 3B: 19.9 (#135), Phi 3 Medium 4k Instruct: —
| Benchmark | Llama 3.2 3B | Phi 3 Medium 4k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |
Reasoning Too close to call
Llama 3.2 3B: 20.1 (#225), Phi 3 Medium 4k Instruct: 20.8 (#214)
| Benchmark | Llama 3.2 3B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1095 | 1127 |
Math Too close to call
Llama 3.2 3B: 29.9 (#213), Phi 3 Medium 4k Instruct: 30.9 (#202)
| Benchmark | Llama 3.2 3B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1126 | 1173 |
Knowledge Too close to call
Llama 3.2 3B: 29.1 (#232), Phi 3 Medium 4k Instruct: 29.6 (#226)
| Benchmark | Llama 3.2 3B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1090 | 1108 |
Multilingual Phi 3 Medium 4k Instruct leads
Llama 3.2 3B: 26.4 (#276), Phi 3 Medium 4k Instruct: 30.8 (#258)
| Benchmark | Llama 3.2 3B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1019 | 1094 |
| LMArena Chinese | 1017 | 1108 |
| LMArena German | 1056 | 1101 |
| LMArena Russian | 949 | 1145 |
| LMArena French | — | 1109 |
| LMArena Japanese | — | 1042 |
| LMArena Korean | — | 954 |
| LMArena Spanish | — | 1095 |
Instruction Following Phi 3 Medium 4k Instruct leads
Llama 3.2 3B: 56.3 (#270), Phi 3 Medium 4k Instruct: 57.8 (#263)
| Benchmark | Llama 3.2 3B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1089 | 1114 |
Long Context Too close to call
Llama 3.2 3B: 33.4 (#256), Phi 3 Medium 4k Instruct: 33.9 (#250)
| Benchmark | Llama 3.2 3B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1101 | 1120 |
Writing & Preference Phi 3 Medium 4k Instruct leads
Llama 3.2 3B: 24.9 (#302), Phi 3 Medium 4k Instruct: 34.3 (#267)
| Benchmark | Llama 3.2 3B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1110 | 1138 |
| LMArena Creative Writing | 1094 | 1106 |
| LMArena Multi-Turn | 1105 | 1088 |
| EQ-Bench Creative Writing | 595 | — |
Frequently asked questions
Is Llama 3.2 3B better than Phi 3 Medium 4k Instruct?
Phi 3 Medium 4k Instruct is the stronger model overall, scoring 32.4 to 28.4 on the Noometry Index.
Is Llama 3.2 3B or Phi 3 Medium 4k Instruct better for coding?
Phi 3 Medium 4k Instruct scores higher on coding benchmarks: 32.3 versus 27.1 in the Noometry coding category.
How many benchmarks do Llama 3.2 3B and Phi 3 Medium 4k Instruct share?
13 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.