Model comparison
Llama 2-34B vs phi-3-medium 14B
phi-3-medium 14B has enough public results to be ranked (#306); Llama 2-34B does not yet, so treat this comparison as directional.
Last verified . 7 shared benchmarks.
Meta
MicrosoftSummary
- They share 7 benchmarks with published results for both.
- phi-3-medium 14B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-34B | phi-3-medium 14B | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | — | 29.1 |
| Released | 2023-07-18 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 2-34B: —, phi-3-medium 14B: 36.3 (#198)
| Benchmark | Llama 2-34B | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| BigCodeBench Complete | — | 48.7% |
Reasoning Not comparable
Llama 2-34B: —, phi-3-medium 14B: —
| Benchmark | Llama 2-34B | phi-3-medium 14B |
|---|---|---|
| BIG-Bench Hard | 44.1% | 81.4% |
| Epoch Capabilities Index | 104.81 | 121.18 |
| WinoGrande | 76.7% | 81.5% |
| Adversarial NLI | — | 55.8% |
| HellaSwag | — | 82.4% |
| PIQA | 81.9% | — |
Math Not comparable
Llama 2-34B: —, phi-3-medium 14B: 25.2 (#249)
| Benchmark | Llama 2-34B | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | — | 17.6% |
| GSM8K | 42.2% | — |
Knowledge Not comparable
Llama 2-34B: —, phi-3-medium 14B: 9.1 (#301)
| Benchmark | Llama 2-34B | phi-3-medium 14B |
|---|---|---|
| ARC (AI2) Challenge | 54.5% | 91.6% |
| MMLU | 62.6% | 78% |
| OpenBookQA | 58.2% | 87.4% |
| TriviaQA | 84.6% | 73.9% |
| GPQA Diamond | — | 27.6% |
| BoolQ | 83.7% | — |
Frequently asked questions
Is Llama 2-34B better than phi-3-medium 14B?
phi-3-medium 14B has enough public results to be ranked (#306); Llama 2-34B does not yet, so treat this comparison as directional.
How many benchmarks do Llama 2-34B and phi-3-medium 14B share?
7 benchmarks have published results for both models. Llama 2-34B has 10 scored results on Noometry and phi-3-medium 14B has 13.