Model comparison
Phi 3 Mini 4k Instruct vs Phi-4 Mini
Phi-4 Mini is the stronger model overall, scoring 30.9 to 27.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in reasoning, where Phi-4 Mini leads 22.4 to 14.1.
Side by side
| Phi 3 Mini 4k Instruct | Phi-4 Mini | |
|---|---|---|
| Provider | Microsoft | Microsoft |
| Noometry Index | 27.9 | 30.9 |
| Released | 2024-04-23 | 2024-12-11 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.075 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 35 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi-4 Mini leads
Phi 3 Mini 4k Instruct: 26.6 (#323), Phi-4 Mini: 28.1 (#317)
| Benchmark | Phi 3 Mini 4k Instruct | Phi-4 Mini |
|---|---|---|
| SciCode | — | 10.8% |
| LiveBench Coding | 15.5% | — |
| LMArena Coding | 1093 | — |
| HumanEval+ | 59.1% | — |
| MBPP+ | 54.2% | — |
Reasoning Phi-4 Mini leads
Phi 3 Mini 4k Instruct: 14.1 (#328), Phi-4 Mini: 22.4 (#195)
| Benchmark | Phi 3 Mini 4k Instruct | Phi-4 Mini |
|---|---|---|
| CritPt | — | 0% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 26.8% | — |
| LMArena Hard Prompts | 1072 | — |
| LiveBench Data Analysis | 34.7% | — |
| Adversarial NLI | 52.8% | — |
| BIG-Bench Hard | 71.7% | — |
| HellaSwag | 76.7% | — |
| LiveBench | 22.4% | — |
| WinoGrande | 70.8% | — |
Math Not comparable
Phi 3 Mini 4k Instruct: 26.6 (#257), Phi-4 Mini: —
| Benchmark | Phi 3 Mini 4k Instruct | Phi-4 Mini |
|---|---|---|
| LiveBench Math | 15.7% | — |
| LMArena Math | 1111 | — |
Knowledge Phi 3 Mini 4k Instruct leads
Phi 3 Mini 4k Instruct: 28.5 (#246), Phi-4 Mini: 25.3 (#262)
| Benchmark | Phi 3 Mini 4k Instruct | Phi-4 Mini |
|---|---|---|
| Vectara Hallucination Rate | — | 23.5% |
| LMArena Expert | 1045 | — |
| ARC (AI2) Challenge | 84.9% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 64% | — |
Multilingual Not comparable
Phi 3 Mini 4k Instruct: 26.3 (#280), Phi-4 Mini: —
| Benchmark | Phi 3 Mini 4k Instruct | Phi-4 Mini |
|---|---|---|
| LMArena Non-English | 1021 | — |
| LMArena Chinese | 1021 | — |
| LMArena French | 1076 | — |
| LMArena German | 1044 | — |
| LMArena Japanese | 935 | — |
| LMArena Korean | 905 | — |
| LMArena Russian | 1022 | — |
| LMArena Spanish | 1085 | — |
Instruction Following Not comparable
Phi 3 Mini 4k Instruct: 47.7 (#303), Phi-4 Mini: —
| Benchmark | Phi 3 Mini 4k Instruct | Phi-4 Mini |
|---|---|---|
| LiveBench Instruction Following | 39.1% | — |
| LMArena Instruction Following | 1053 | — |
Long Context Not comparable
Phi 3 Mini 4k Instruct: 31.7 (#276), Phi-4 Mini: —
| Benchmark | Phi 3 Mini 4k Instruct | Phi-4 Mini |
|---|---|---|
| LMArena Longer Query | 1044 | — |
Writing & Preference Not comparable
Phi 3 Mini 4k Instruct: 27.6 (#300), Phi-4 Mini: —
| Benchmark | Phi 3 Mini 4k Instruct | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1073 | — |
| LMArena Creative Writing | 1037 | — |
| LMArena Multi-Turn | 1018 | — |
| LiveBench Language | 9.2% | — |
Frequently asked questions
Is Phi 3 Mini 4k Instruct better than Phi-4 Mini?
Phi-4 Mini is the stronger model overall, scoring 30.9 to 27.9 on the Noometry Index.
Is Phi 3 Mini 4k Instruct or Phi-4 Mini better for coding?
Phi-4 Mini scores higher on coding benchmarks: 28.1 versus 26.6 in the Noometry coding category.
How many benchmarks do Phi 3 Mini 4k Instruct and Phi-4 Mini share?
0 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Phi-4 Mini has 3.