Model comparison
Llama 2-34B vs Phi-4 Mini
Phi-4 Mini has enough public results to be ranked (#283); Llama 2-34B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Meta
MicrosoftSummary
- Phi-4 Mini has downloadable open weights; the other is API-only.
Side by side
| Llama 2-34B | Phi-4 Mini | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | — | 30.9 |
| Released | 2023-07-18 | 2024-12-11 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.075 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 10 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 2-34B: —, Phi-4 Mini: 28.1 (#317)
| Benchmark | Llama 2-34B | Phi-4 Mini |
|---|---|---|
| SciCode | — | 10.8% |
Reasoning Not comparable
Llama 2-34B: —, Phi-4 Mini: 22.4 (#195)
| Benchmark | Llama 2-34B | Phi-4 Mini |
|---|---|---|
| CritPt | — | 0% |
| BIG-Bench Hard | 44.1% | — |
| Epoch Capabilities Index | 105.2 | — |
| PIQA | 81.9% | — |
| WinoGrande | 76.7% | — |
Math Not comparable
Llama 2-34B: —, Phi-4 Mini: —
| Benchmark | Llama 2-34B | Phi-4 Mini |
|---|---|---|
| GSM8K | 42.2% | — |
Knowledge Not comparable
Llama 2-34B: —, Phi-4 Mini: 25.3 (#262)
| Benchmark | Llama 2-34B | Phi-4 Mini |
|---|---|---|
| Vectara Hallucination Rate | — | 23.5% |
| ARC (AI2) Challenge | 54.5% | — |
| BoolQ | 83.7% | — |
| MMLU | 62.6% | — |
| OpenBookQA | 58.2% | — |
| TriviaQA | 84.6% | — |
Frequently asked questions
Is Llama 2-34B better than Phi-4 Mini?
Phi-4 Mini has enough public results to be ranked (#283); Llama 2-34B does not yet, so treat this comparison as directional.
How many benchmarks do Llama 2-34B and Phi-4 Mini share?
0 benchmarks have published results for both models. Llama 2-34B has 10 scored results on Noometry and Phi-4 Mini has 3.