Model comparison
Llama 3.2 3B vs Phi 3 Mini 128k Instruct
Llama 3.2 3B and Phi 3 Mini 128k Instruct score almost the same on the Noometry Index (28.9 vs 29.7), so choose on price, context window or the category you care about most.
Last verified . 15 shared benchmarks.
Meta
MicrosoftSummary
- They share 15 benchmarks with published results for both. Llama 3.2 3B scores higher in 6 categories and Phi 3 Mini 128k Instruct in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama 3.2 3B leads 56.0 to 51.8.
- The biggest single-benchmark swing is BigCodeBench Complete: 28.3% for Llama 3.2 3B and 40.6% for Phi 3 Mini 128k Instruct.
Side by side
| Llama 3.2 3B | Phi 3 Mini 128k Instruct | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 28.9 | 29.7 |
| Released | 2024-09-24 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 118K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 18 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi 3 Mini 128k Instruct leads
Llama 3.2 3B: 27.6 (#319), Phi 3 Mini 128k Instruct: 28.8 (#312)
| Benchmark | Llama 3.2 3B | Phi 3 Mini 128k Instruct |
|---|---|---|
| BigCodeBench Instruct | 23.4% | 29.6% |
| LMArena Coding | 1098 | 1039 |
| BigCodeBench Complete | 28.3% | 40.6% |
Agentic & Tool Use Not comparable
Llama 3.2 3B: 20.1 (#143), Phi 3 Mini 128k Instruct: —
| Benchmark | Llama 3.2 3B | Phi 3 Mini 128k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |
Reasoning Llama 3.2 3B leads
Llama 3.2 3B: 21.0 (#228), Phi 3 Mini 128k Instruct: 19.6 (#256)
| Benchmark | Llama 3.2 3B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1095 | 1028 |
Math Too close to call
Llama 3.2 3B: 32.4 (#214), Phi 3 Mini 128k Instruct: 31.6 (#222)
| Benchmark | Llama 3.2 3B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1126 | 1089 |
Knowledge Llama 3.2 3B leads
Llama 3.2 3B: 29.7 (#235), Phi 3 Mini 128k Instruct: 26.8 (#254)
| Benchmark | Llama 3.2 3B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1090 | 984 |
Multilingual Llama 3.2 3B leads
Llama 3.2 3B: 26.2 (#281), Phi 3 Mini 128k Instruct: 25.2 (#285)
| Benchmark | Llama 3.2 3B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1019 | 1000 |
| LMArena Chinese | 1017 | 1016 |
| LMArena German | 1056 | 1006 |
| LMArena Russian | 949 | 1004 |
| LMArena French | — | 1039 |
| LMArena Japanese | — | 899 |
| LMArena Korean | — | 856 |
| LMArena Spanish | — | 1059 |
Instruction Following Llama 3.2 3B leads
Llama 3.2 3B: 56.0 (#275), Phi 3 Mini 128k Instruct: 51.8 (#294)
| Benchmark | Llama 3.2 3B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1089 | 1023 |
Long Context Llama 3.2 3B leads
Llama 3.2 3B: 33.4 (#261), Phi 3 Mini 128k Instruct: 30.4 (#289)
| Benchmark | Llama 3.2 3B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1100 | 996 |
Writing & Preference Phi 3 Mini 128k Instruct leads
Llama 3.2 3B: 24.7 (#307), Phi 3 Mini 128k Instruct: 27.1 (#301)
| Benchmark | Llama 3.2 3B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1110 | 1050 |
| LMArena Creative Writing | 1094 | 1024 |
| LMArena Multi-Turn | 1105 | 989 |
| EQ-Bench Creative Writing | 595 | — |
Frequently asked questions
Is Llama 3.2 3B better than Phi 3 Mini 128k Instruct?
Llama 3.2 3B and Phi 3 Mini 128k Instruct score almost the same on the Noometry Index (28.9 vs 29.7), so choose on price, context window or the category you care about most.
Is Llama 3.2 3B or Phi 3 Mini 128k Instruct better for coding?
Phi 3 Mini 128k Instruct scores higher on coding benchmarks: 28.8 versus 27.6 in the Noometry coding category.
How many benchmarks do Llama 3.2 3B and Phi 3 Mini 128k Instruct share?
15 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.