Model comparison
Llama 2-34B vs Phi-3.5-mini
Neither Llama 2-34B nor Phi-3.5-mini has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 3 shared benchmarks.
Meta
MicrosoftSummary
- They share 3 benchmarks with published results for both.
- Phi-3.5-mini has downloadable open weights; the other is API-only.
Side by side
| Llama 2-34B | Phi-3.5-mini | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | — | 36.9 |
| Released | 2023-07-18 | 2024-08-16 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 2-34B: —, Phi-3.5-mini: 34.6 (#232)
| Benchmark | Llama 2-34B | Phi-3.5-mini |
|---|---|---|
| BigCodeBench Instruct | — | 32.8% |
| BigCodeBench Complete | — | 38.5% |
Reasoning Not comparable
Llama 2-34B: —, Phi-3.5-mini: —
| Benchmark | Llama 2-34B | Phi-3.5-mini |
|---|---|---|
| PIQA | 81.9% | 81% |
| BIG-Bench Hard | 44.1% | — |
| Epoch Capabilities Index | 105.2 | — |
| WinoGrande | 76.7% | — |
Math Not comparable
Llama 2-34B: —, Phi-3.5-mini: —
| Benchmark | Llama 2-34B | Phi-3.5-mini |
|---|---|---|
| GSM8K | 42.2% | 86.2% |
Knowledge Not comparable
Llama 2-34B: —, Phi-3.5-mini: —
| Benchmark | Llama 2-34B | Phi-3.5-mini |
|---|---|---|
| BoolQ | 83.7% | 78% |
| ARC (AI2) Challenge | 54.5% | — |
| MMLU | 62.6% | — |
| OpenBookQA | 58.2% | — |
| TriviaQA | 84.6% | — |
Frequently asked questions
Is Llama 2-34B better than Phi-3.5-mini?
Neither Llama 2-34B nor Phi-3.5-mini has enough public benchmark results to be ranked yet; the rows below show what has been published.
How many benchmarks do Llama 2-34B and Phi-3.5-mini share?
3 benchmarks have published results for both models. Llama 2-34B has 10 scored results on Noometry and Phi-3.5-mini has 5.