Model comparison
Llama 3.2 3B vs Phi 3 Mini 4k Instruct
Llama 3.2 3B is the stronger model overall, scoring 28.9 to 27.9 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 6 categories and Phi 3 Mini 4k 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 47.7.
Side by side
| Llama 3.2 3B | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 28.9 | 27.9 |
| 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 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.2 3B leads
Llama 3.2 3B: 27.6 (#319), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Llama 3.2 3B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1098 | 1093 |
| BigCodeBench Instruct | 23.4% | — |
| LiveBench Coding | — | 15.5% |
| BigCodeBench Complete | 28.3% | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
Llama 3.2 3B: 20.1 (#143), Phi 3 Mini 4k Instruct: —
| Benchmark | Llama 3.2 3B | Phi 3 Mini 4k 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 4k Instruct: 14.1 (#328)
| Benchmark | Llama 3.2 3B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1095 | 1072 |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Llama 3.2 3B leads
Llama 3.2 3B: 32.4 (#214), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Llama 3.2 3B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1126 | 1111 |
| LiveBench Math | — | 15.7% |
Knowledge Llama 3.2 3B leads
Llama 3.2 3B: 29.7 (#235), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Llama 3.2 3B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1090 | 1045 |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Too close to call
Llama 3.2 3B: 26.2 (#281), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Llama 3.2 3B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1019 | 1021 |
| LMArena Chinese | 1017 | 1021 |
| LMArena German | 1056 | 1044 |
| LMArena Russian | 949 | 1022 |
| LMArena French | — | 1076 |
| LMArena Japanese | — | 935 |
| LMArena Korean | — | 905 |
| LMArena Spanish | — | 1085 |
Instruction Following Llama 3.2 3B leads
Llama 3.2 3B: 56.0 (#275), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Llama 3.2 3B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1089 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Llama 3.2 3B leads
Llama 3.2 3B: 33.4 (#261), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Llama 3.2 3B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1100 | 1044 |
Writing & Preference Phi 3 Mini 4k Instruct leads
Llama 3.2 3B: 24.7 (#307), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Llama 3.2 3B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1110 | 1073 |
| LMArena Creative Writing | 1094 | 1037 |
| LMArena Multi-Turn | 1105 | 1018 |
| EQ-Bench Creative Writing | 595 | — |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Llama 3.2 3B better than Phi 3 Mini 4k Instruct?
Llama 3.2 3B is the stronger model overall, scoring 28.9 to 27.9 on the Noometry Index.
Is Llama 3.2 3B or Phi 3 Mini 4k Instruct better for coding?
Llama 3.2 3B scores higher on coding benchmarks: 27.6 versus 26.6 in the Noometry coding category.
How many benchmarks do Llama 3.2 3B and Phi 3 Mini 4k Instruct share?
13 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.