Model comparison
Phi-2 vs Yi 6B
Neither Phi-2 nor Yi 6B has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 6 shared benchmarks.
MicrosoftSummary
- They share 6 benchmarks with published results for both.
Side by side
| Phi-2 | Yi 6B | |
|---|---|---|
| Provider | Microsoft | 01.AI |
| Noometry Index | — | — |
| Released | 2023-12-12 | 2023-11-02 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 11 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Phi-2: —, Yi 6B: —
| Benchmark | Phi-2 | Yi 6B |
|---|---|---|
| HumanEval+ | 45.1% | — |
| MBPP+ | 54.2% | — |
Reasoning Not comparable
Phi-2: —, Yi 6B: —
| Benchmark | Phi-2 | Yi 6B |
|---|---|---|
| BIG-Bench Hard | 59.4% | 47.2% |
| Epoch Capabilities Index | 107.94 | 104.77 |
| HellaSwag | 53.6% | 74.4% |
| WinoGrande | 54.7% | 71.3% |
| Adversarial NLI | 42.5% | — |
Math Not comparable
Phi-2: —, Yi 6B: —
| Benchmark | Phi-2 | Yi 6B |
|---|---|---|
| GSM8K | — | 44.9% |
Knowledge Not comparable
Phi-2: —, Yi 6B: —
| Benchmark | Phi-2 | Yi 6B |
|---|---|---|
| ARC (AI2) Challenge | 75.9% | 50.3% |
| MMLU | 58.4% | 64% |
| OpenBookQA | 73.6% | — |
| TriviaQA | 45.2% | — |
Frequently asked questions
Is Phi-2 better than Yi 6B?
Neither Phi-2 nor Yi 6B has enough public benchmark results to be ranked yet; the rows below show what has been published.
How many benchmarks do Phi-2 and Yi 6B share?
6 benchmarks have published results for both models. Phi-2 has 11 scored results on Noometry and Yi 6B has 7.