Model comparison
Phi 3 Small 8k Instruct vs Phi-4 Mini
Phi-4 Mini is the stronger model overall, scoring 30.9 to 29.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in reasoning, where Phi-4 Mini leads 22.4 to 14.8.
Side by side
| Phi 3 Small 8k Instruct | Phi-4 Mini | |
|---|---|---|
| Provider | Microsoft | Microsoft |
| Noometry Index | 29.3 | 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 | 32 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Phi 3 Small 8k Instruct: 27.9 (#318), Phi-4 Mini: 28.1 (#317)
| Benchmark | Phi 3 Small 8k Instruct | Phi-4 Mini |
|---|---|---|
| SciCode | — | 10.8% |
| LiveBench Coding | 20.3% | — |
| LMArena Coding | 1101 | — |
Reasoning Phi-4 Mini leads
Phi 3 Small 8k Instruct: 14.8 (#323), Phi-4 Mini: 22.4 (#195)
| Benchmark | Phi 3 Small 8k Instruct | Phi-4 Mini |
|---|---|---|
| CritPt | — | 0% |
| LiveBench Reasoning | 15.9% | — |
| LMArena Hard Prompts | 1100 | — |
| LiveBench Data Analysis | 30.3% | — |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 79.1% | — |
| HellaSwag | 77% | — |
| LiveBench | 24% | — |
| WinoGrande | 81.5% | — |
Math Not comparable
Phi 3 Small 8k Instruct: 27.6 (#248), Phi-4 Mini: —
| Benchmark | Phi 3 Small 8k Instruct | Phi-4 Mini |
|---|---|---|
| LiveBench Math | 17.6% | — |
| LMArena Math | 1151 | — |
Knowledge Phi 3 Small 8k Instruct leads
Phi 3 Small 8k Instruct: 29.1 (#240), Phi-4 Mini: 25.3 (#262)
| Benchmark | Phi 3 Small 8k Instruct | Phi-4 Mini |
|---|---|---|
| Vectara Hallucination Rate | — | 23.5% |
| LMArena Expert | 1067 | — |
| ARC (AI2) Challenge | 90.7% | — |
| MMLU | 75.7% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 58.1% | — |
Multilingual Not comparable
Phi 3 Small 8k Instruct: 28.5 (#272), Phi-4 Mini: —
| Benchmark | Phi 3 Small 8k Instruct | Phi-4 Mini |
|---|---|---|
| LMArena Non-English | 1058 | — |
| LMArena Chinese | 1061 | — |
| LMArena French | 1135 | — |
| LMArena German | 1080 | — |
| LMArena Japanese | 966 | — |
| LMArena Korean | 894 | — |
| LMArena Russian | 1111 | — |
| LMArena Spanish | 1111 | — |
Instruction Following Not comparable
Phi 3 Small 8k Instruct: 51.9 (#292), Phi-4 Mini: —
| Benchmark | Phi 3 Small 8k Instruct | Phi-4 Mini |
|---|---|---|
| LiveBench Instruction Following | 47.2% | — |
| LMArena Instruction Following | 1087 | — |
Long Context Not comparable
Phi 3 Small 8k Instruct: 33.0 (#267), Phi-4 Mini: —
| Benchmark | Phi 3 Small 8k Instruct | Phi-4 Mini |
|---|---|---|
| LMArena Longer Query | 1088 | — |
Writing & Preference Not comparable
Phi 3 Small 8k Instruct: 31.1 (#284), Phi-4 Mini: —
| Benchmark | Phi 3 Small 8k Instruct | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1110 | — |
| LMArena Creative Writing | 1083 | — |
| LMArena Multi-Turn | 1068 | — |
| LiveBench Language | 12.9% | — |
Frequently asked questions
Is Phi 3 Small 8k Instruct better than Phi-4 Mini?
Phi-4 Mini is the stronger model overall, scoring 30.9 to 29.3 on the Noometry Index.
Is Phi 3 Small 8k Instruct or Phi-4 Mini better for coding?
They score almost the same on coding (27.9 vs 28.1); test both on your own repository before choosing.
How many benchmarks do Phi 3 Small 8k Instruct and Phi-4 Mini share?
0 benchmarks have published results for both models. Phi 3 Small 8k Instruct has 32 scored results on Noometry and Phi-4 Mini has 3.