Model comparison
Falcon-40B vs phi-3-medium 14B
phi-3-medium 14B has enough public results to be ranked (#306); Falcon-40B does not yet, so treat this comparison as directional.
Last verified . 8 shared benchmarks.
Technology Innovation Institute
MicrosoftSummary
- They share 8 benchmarks with published results for both.
Side by side
| Falcon-40B | phi-3-medium 14B | |
|---|---|---|
| Provider | Technology Innovation Institute | Microsoft |
| Noometry Index | — | 29.7 |
| Released | 2023-03-15 | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 12 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-40B: —, phi-3-medium 14B: 36.8 (#201)
| Benchmark | Falcon-40B | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| BigCodeBench Complete | — | 48.7% |
Reasoning Not comparable
Falcon-40B: —, phi-3-medium 14B: —
| Benchmark | Falcon-40B | phi-3-medium 14B |
|---|---|---|
| BIG-Bench Hard | 37.1% | 81.4% |
| Epoch Capabilities Index | 104.45 | 121.23 |
| HellaSwag | 85.3% | 82.4% |
| WinoGrande | 76.9% | 81.5% |
| Adversarial NLI | — | 55.8% |
| LAMBADA | 77.3% | — |
| PIQA | 83% | — |
Math Not comparable
Falcon-40B: —, phi-3-medium 14B: 27.3 (#250)
| Benchmark | Falcon-40B | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | — | 17.6% |
| GSM8K | 33.8% | — |
Knowledge Not comparable
Falcon-40B: —, phi-3-medium 14B: 9.1 (#306)
| Benchmark | Falcon-40B | phi-3-medium 14B |
|---|---|---|
| ARC (AI2) Challenge | 61.9% | 91.6% |
| MMLU | 56.9% | 78% |
| OpenBookQA | 56.6% | 87.4% |
| TriviaQA | 79.9% | 73.9% |
| GPQA Diamond | — | 27.6% |
| BoolQ | 83.1% | — |
Frequently asked questions
Is Falcon-40B better than phi-3-medium 14B?
phi-3-medium 14B has enough public results to be ranked (#306); Falcon-40B does not yet, so treat this comparison as directional.
How many benchmarks do Falcon-40B and phi-3-medium 14B share?
8 benchmarks have published results for both models. Falcon-40B has 12 scored results on Noometry and phi-3-medium 14B has 13.