Model comparison
Falcon-180B vs Phi-2
Falcon-180B has enough public results to be ranked (#254); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 6 shared benchmarks.
Technology Innovation Institute
MicrosoftSummary
- They share 6 benchmarks with published results for both.
Side by side
| Falcon-180B | Phi-2 | |
|---|---|---|
| Provider | Technology Innovation Institute | Microsoft |
| Noometry Index | 31.8 | — |
| Released | 2023-09-06 | 2023-12-12 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 16 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-180B: —, Phi-2: —
| Benchmark | Falcon-180B | Phi-2 |
|---|---|---|
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |
Reasoning Not comparable
Falcon-180B: 18.3 (#266), Phi-2: —
| Benchmark | Falcon-180B | Phi-2 |
|---|---|---|
| Epoch Capabilities Index | 111.89 | 107.62 |
| HellaSwag | 89% | 53.6% |
| WinoGrande | 87.1% | 54.7% |
| LMArena Hard Prompts | 1007 | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| LAMBADA | 79.8% | — |
| PIQA | 84.9% | — |
Math Not comparable
Falcon-180B: —, Phi-2: —
| Benchmark | Falcon-180B | Phi-2 |
|---|---|---|
| GSM8K | 54.4% | — |
Knowledge Not comparable
Falcon-180B: —, Phi-2: —
| Benchmark | Falcon-180B | Phi-2 |
|---|---|---|
| ARC (AI2) Challenge | 67.8% | 75.9% |
| MMLU | 70.6% | 58.4% |
| OpenBookQA | 64.2% | 73.6% |
| BoolQ | 89% | — |
| TriviaQA | — | 45.2% |
Multilingual Not comparable
Falcon-180B: 25.3 (#281), Phi-2: —
| Benchmark | Falcon-180B | Phi-2 |
|---|---|---|
| LMArena Non-English | 1000 | — |
Instruction Following Not comparable
Falcon-180B: 53.6 (#281), Phi-2: —
| Benchmark | Falcon-180B | Phi-2 |
|---|---|---|
| LMArena Instruction Following | 1047 | — |
Writing & Preference Not comparable
Falcon-180B: 29.3 (#290), Phi-2: —
| Benchmark | Falcon-180B | Phi-2 |
|---|---|---|
| LMArena Text | 1054 | — |
| LMArena Creative Writing | 1089 | — |
| LMArena Multi-Turn | 1013 | — |
Frequently asked questions
Is Falcon-180B better than Phi-2?
Falcon-180B has enough public results to be ranked (#254); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do Falcon-180B and Phi-2 share?
6 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and Phi-2 has 11.