Model comparison
Falcon-7B vs Phi-2
Neither Falcon-7B nor Phi-2 has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 8 shared benchmarks.
Technology Innovation Institute
MicrosoftSummary
- They share 8 benchmarks with published results for both.
Side by side
| Falcon-7B | Phi-2 | |
|---|---|---|
| Provider | Technology Innovation Institute | Microsoft |
| Noometry Index | — | — |
| Released | 2023-04-24 | 2023-12-12 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 12 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-7B: —, Phi-2: —
| Benchmark | Falcon-7B | Phi-2 |
|---|---|---|
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |
Reasoning Not comparable
Falcon-7B: —, Phi-2: —
| Benchmark | Falcon-7B | Phi-2 |
|---|---|---|
| BIG-Bench Hard | 28.8% | 59.4% |
| Epoch Capabilities Index | 95.1 | 107.94 |
| HellaSwag | 78.1% | 53.6% |
| WinoGrande | 67.2% | 54.7% |
| Adversarial NLI | — | 42.5% |
| LAMBADA | 74.9% | — |
| PIQA | 80.3% | — |
Math Not comparable
Falcon-7B: —, Phi-2: —
| Benchmark | Falcon-7B | Phi-2 |
|---|---|---|
| GSM8K | 6.8% | — |
Knowledge Not comparable
Falcon-7B: —, Phi-2: —
| Benchmark | Falcon-7B | Phi-2 |
|---|---|---|
| ARC (AI2) Challenge | 47.9% | 75.9% |
| MMLU | 35% | 58.4% |
| OpenBookQA | 51.6% | 73.6% |
| TriviaQA | 64.6% | 45.2% |
| BoolQ | 75.3% | — |
Frequently asked questions
Is Falcon-7B better than Phi-2?
Neither Falcon-7B nor Phi-2 has enough public benchmark results to be ranked yet; the rows below show what has been published.
How many benchmarks do Falcon-7B and Phi-2 share?
8 benchmarks have published results for both models. Falcon-7B has 12 scored results on Noometry and Phi-2 has 11.